{ "metadata": { "title": "IPTV transcript atlas", "utterance_duration_range_seconds": [ 0.1, 60 ], "generated_at": "2026-10-13T17:25:54.235787+00:00", "languages": [ "English", "Spanish", "Hindi" ], "emotions": [ "Angry", "Annoyed", "Disgusted", "Fearful", "Happy", "Neutral", "Sad", "Surprised" ], "clips_per_cell": 3, "requested_clips": 216, "energy_thresholds": { "low_max": 0.51953125, "medium_max": 0.58203125, "units": "Hotdog normalized model score, 0–1", "method": "Frozen pooled empirical tertiles of 24,646 eligible utterances in the first randomly pivot-sampled completed-job batch; low < low_max, medium >= low_max and < medium_max, high >= medium_max. This score is not loudness in dB." }, "sampling_method": "Uniform random UUID pivots and bounded primary-key ranges of completed jobs; baseline utterances are 0.5–20 seconds; rare-cell supplements allow complete 0.1–60 second utterances. Hotdog analyzes a center window up to 20 seconds, not the whole longer utterance. All have finite final MOS >=2.8, have nonempty original and new transcripts, Hotdog emotion/energy, and all Qwen-detected chunks agree on target language. Supplemental discovery used the completed Hindi-routing acceptance cohort and additional random global jobs, then 2,000 catalog-Hindi and 2,000 catalog-Spanish jobs. Catalog language only prioritizes downloads; all actual ASR chunks must still agree on the displayed language. All supplements retain the frozen baseline thresholds. Distinct transcript text and source-job diversity preferred; no WER-based selection.", "baseline_eligible_utterances": 24646, "eligible_utterances_inspected": 367894, "baseline_language_counts": { "English": 17680, "Spanish": 6305, "Hindi": 661 }, "jobs_inspected": 26001, "coverage": [ { "language": "English", "emotion": "Angry", "energy": "low", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Angry", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Angry", "energy": "high", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Annoyed", "energy": "low", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Annoyed", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Annoyed", "energy": "high", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Disgusted", "energy": "low", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Disgusted", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Disgusted", "energy": "high", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Fearful", "energy": "low", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Fearful", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Fearful", "energy": "high", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Happy", "energy": "low", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Happy", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Happy", "energy": "high", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Neutral", "energy": "low", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Neutral", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Neutral", "energy": "high", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Sad", "energy": "low", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Sad", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Sad", "energy": "high", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Surprised", "energy": "low", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Surprised", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "English", "emotion": "Surprised", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Angry", "energy": "low", "requested": 3, "actual": 0 }, { "language": "Spanish", "emotion": "Angry", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Angry", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Annoyed", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Annoyed", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Annoyed", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Disgusted", "energy": "low", "requested": 3, "actual": 0 }, { "language": "Spanish", "emotion": "Disgusted", "energy": "medium", "requested": 3, "actual": 0 }, { "language": "Spanish", "emotion": "Disgusted", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Fearful", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Fearful", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Fearful", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Happy", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Happy", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Happy", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Neutral", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Neutral", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Neutral", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Sad", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Sad", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Sad", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Surprised", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Surprised", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Spanish", "emotion": "Surprised", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Angry", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Angry", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Angry", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Annoyed", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Annoyed", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Annoyed", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Disgusted", "energy": "low", "requested": 3, "actual": 0 }, { "language": "Hindi", "emotion": "Disgusted", "energy": "medium", "requested": 3, "actual": 0 }, { "language": "Hindi", "emotion": "Disgusted", "energy": "high", "requested": 3, "actual": 2 }, { "language": "Hindi", "emotion": "Fearful", "energy": "low", "requested": 3, "actual": 0 }, { "language": "Hindi", "emotion": "Fearful", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Fearful", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Happy", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Happy", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Happy", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Neutral", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Neutral", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Neutral", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Sad", "energy": "low", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Sad", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Sad", "energy": "high", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Surprised", "energy": "low", "requested": 3, "actual": 1 }, { "language": "Hindi", "emotion": "Surprised", "energy": "medium", "requested": 3, "actual": 3 }, { "language": "Hindi", "emotion": "Surprised", "energy": "high", "requested": 3, "actual": 3 } ], "comparison_note": "WER measures disagreement with the original machine transcript, not accuracy against human ground truth. Original control/language tags are excluded from WER; verbatim original is retained.", "audio_note": "Exact 48 kHz source crop, resampled using the pipeline to 16 kHz; float32 waveform SHA verified against the completed manifest. Enhanced segments use the cleaned sidecar, otherwise the original source. Listening WAVs use PCM16 where rounding fits its range, and float32 WAV for the seven over-range clips, preserving source peaks without saturation. No volume normalization is applied. Spectrogram and waveform use the verified pre-export float32 crop.", "manifest_validation": "All selected completion manifests validated, source manifests SHA-verified, and source crop waveform SHA-verified.", "discovery_summary": { "completed_jobs_inspected": 26001, "eligible_utterances_inspected": 367894, "manifest_errors": 0, "targeted_supplement": { "metadata_rows_read": 110000, "catalog_candidates": { "hin": 2000, "spa": 2000 }, "jobs_inspected": 4000, "method": "Catalog Hindi/Spanish folders only prioritize downloads from bounded status/id-index ranges; complete utterances still require all ASR chunks to agree on actual target language." } }, "source_availability": [ { "language": "English", "emotion": "Angry", "energy": "low", "available": 20, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Angry", "energy": "medium", "available": 111, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Angry", "energy": "high", "available": 9148, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Annoyed", "energy": "low", "available": 653, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Annoyed", "energy": "medium", "available": 2455, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Annoyed", "energy": "high", "available": 10145, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Disgusted", "energy": "low", "available": 3, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Disgusted", "energy": "medium", "available": 6, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Disgusted", "energy": "high", "available": 53, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Fearful", "energy": "low", "available": 65, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Fearful", "energy": "medium", "available": 97, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Fearful", "energy": "high", "available": 286, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Happy", "energy": "low", "available": 2168, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Happy", "energy": "medium", "available": 9194, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Happy", "energy": "high", "available": 23894, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Neutral", "energy": "low", "available": 43953, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Neutral", "energy": "medium", "available": 33529, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Neutral", "energy": "high", "available": 8028, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Sad", "energy": "low", "available": 1977, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Sad", "energy": "medium", "available": 772, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Sad", "energy": "high", "available": 541, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Surprised", "energy": "low", "available": 105, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Surprised", "energy": "medium", "available": 493, "selected": 3, "requested": 3 }, { "language": "English", "emotion": "Surprised", "energy": "high", "available": 3665, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Angry", "energy": "low", "available": 0, "selected": 0, "requested": 3 }, { "language": "Spanish", "emotion": "Angry", "energy": "medium", "available": 22, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Angry", "energy": "high", "available": 4805, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Annoyed", "energy": "low", "available": 221, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Annoyed", "energy": "medium", "available": 1505, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Annoyed", "energy": "high", "available": 6772, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Disgusted", "energy": "low", "available": 0, "selected": 0, "requested": 3 }, { "language": "Spanish", "emotion": "Disgusted", "energy": "medium", "available": 0, "selected": 0, "requested": 3 }, { "language": "Spanish", "emotion": "Disgusted", "energy": "high", "available": 9, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Fearful", "energy": "low", "available": 4, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Fearful", "energy": "medium", "available": 12, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Fearful", "energy": "high", "available": 77, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Happy", "energy": "low", "available": 425, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Happy", "energy": "medium", "available": 3405, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Happy", "energy": "high", "available": 10261, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Neutral", "energy": "low", "available": 21928, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Neutral", "energy": "medium", "available": 29464, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Neutral", "energy": "high", "available": 7836, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Sad", "energy": "low", "available": 525, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Sad", "energy": "medium", "available": 345, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Sad", "energy": "high", "available": 332, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Surprised", "energy": "low", "available": 13, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Surprised", "energy": "medium", "available": 129, "selected": 3, "requested": 3 }, { "language": "Spanish", "emotion": "Surprised", "energy": "high", "available": 952, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Angry", "energy": "low", "available": 12, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Angry", "energy": "medium", "available": 554, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Angry", "energy": "high", "available": 32811, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Annoyed", "energy": "low", "available": 76, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Annoyed", "energy": "medium", "available": 1683, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Annoyed", "energy": "high", "available": 15952, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Disgusted", "energy": "low", "available": 0, "selected": 0, "requested": 3 }, { "language": "Hindi", "emotion": "Disgusted", "energy": "medium", "available": 0, "selected": 0, "requested": 3 }, { "language": "Hindi", "emotion": "Disgusted", "energy": "high", "available": 2, "selected": 2, "requested": 3 }, { "language": "Hindi", "emotion": "Fearful", "energy": "low", "available": 0, "selected": 0, "requested": 3 }, { "language": "Hindi", "emotion": "Fearful", "energy": "medium", "available": 3, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Fearful", "energy": "high", "available": 25, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Happy", "energy": "low", "available": 173, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Happy", "energy": "medium", "available": 1852, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Happy", "energy": "high", "available": 11740, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Neutral", "energy": "low", "available": 6806, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Neutral", "energy": "medium", "available": 32826, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Neutral", "energy": "high", "available": 19974, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Sad", "energy": "low", "available": 734, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Sad", "energy": "medium", "available": 955, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Sad", "energy": "high", "available": 816, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Surprised", "energy": "low", "available": 1, "selected": 1, "requested": 3 }, { "language": "Hindi", "emotion": "Surprised", "energy": "medium", "available": 15, "selected": 3, "requested": 3 }, { "language": "Hindi", "emotion": "Surprised", "energy": "high", "available": 481, "selected": 3, "requested": 3 } ], "coverage_note": "195 of 216 requested examples found after inspecting 26,001 completed jobs and 367,894 eligible utterances. Eight cells have fewer than three examples in the inspected sample; this is not a claim that the entire corpus lacks those utterances.", "audio_export": { "pcm16_clips": 188, "float32_clips": 7, "source_clips_with_abs_peak_above_1": 7, "maximum_source_abs_peak": 1.2545, "saturation_applied": false, "method": "Round to PCM16 only when every rounded value is representable; otherwise export the exact original float32 samples. All source amplitudes are preserved within the selected WAV encoding." } }, "samples": [ { "language": "English", "emotion": "Angry", "emotion_confidence": 0.4128000736236572, "duration_seconds": 4.453999999999997, "mos": 3.0801, "audio_variant": "original", "original_transcript_raw": "Twenty years you get away with it in my country you go to jail. ", "original_transcript": "Twenty years you get away with it in my country you go to jail.", "retranscribed_transcript": "Twenty years, you get away with it. In my country, you go to jail.", "backend": "qwen", "emotion_analyzed_seconds": 4.454, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-001", "energy": { "value": 0.51171875, "bucket": "low" }, "audio_url": "audio/utterance-001.wav", "spectrogram_url": "spectrograms/utterance-001.png", "waveform": [ 0.04303, 0.04481, 0.04834, 0.04288, 0.20674, 0.22887, 0.2605, 0.2401, 0.23524, 0.15134, 0.15989, 0.15343, 0.13355, 0.11513, 0.1103, 0.10402, 0.09346, 0.09846, 0.09684, 0.1467, 0.18748, 0.20323, 0.19127, 0.19568, 0.11415, 0.10959, 0.06422, 0.05534, 0.06137, 0.07279, 0.08053, 0.08011, 0.03822, 0.02456, 0.03815, 0.03544, 0.10701, 0.16419, 0.18955, 0.0498, 0.06453, 0.17718, 0.14352, 0.09361, 0.08604, 0.10262, 0.10685, 0.13012, 0.12512, 0.1453, 0.10929, 0.07956, 0.04937, 0.08954, 0.09306, 0.08454, 0.02835, 0.02418, 0.04331, 0.04484, 0.03039, 0.02194, 0.02082, 0.03899, 0.05204, 0.02873, 0.02015, 0.01685, 0.01688, 0.01556, 0.01581, 0.0208, 0.02118, 0.02238, 0.02682, 0.01699, 0.02283, 0.01934, 0.02053, 0.02108, 0.01534, 0.0157, 0.01971, 0.01843, 0.01838, 0.01714, 0.01849, 0.01648, 0.01551, 0.02267, 0.02058, 0.02027, 0.02282, 0.02091, 0.02624, 0.02603, 0.0289, 0.02563, 0.02589, 0.02814, 0.02685, 0.02478, 0.02416, 0.02672, 0.0302, 0.06655, 0.04272, 0.05658, 0.04277, 0.06445, 0.05799, 0.36888, 0.32284, 0.46956, 0.43477, 0.43616, 0.26765, 0.0527, 0.03483, 0.03249, 0.16126, 0.08118, 0.17054, 0.28367, 0.20464, 0.11976, 0.04983, 0.05197, 0.12431, 0.13364, 0.09236, 0.09332, 0.0867, 0.06345, 0.07845, 0.05594, 0.08674, 0.06439, 0.0575, 0.02953, 0.0353, 0.07402, 0.06486, 0.17119, 0.21106, 0.2074, 0.13615, 0.10096, 0.19109, 0.14759, 0.10228, 0.03411, 0.02359, 0.0252, 0.02113, 0.02114, 0.02287, 0.03876, 0.07984, 0.07219, 0.0989, 0.22782, 0.26063, 0.23985, 0.21403, 0.23922, 0.16486, 0.15806, 0.0952, 0.12269, 0.13361, 0.06664, 0.06431, 0.05999, 0.06995, 0.07036, 0.04154, 0.02983, 0.02041, 0.02714 ], "comparison": { "original": "Twenty years you get away with it in my country you go to jail.", "retranscribed": "Twenty years, you get away with it. In my country, you go to jail.", "reference_tokens": [ "twenty", "years", "you", "get", "away", "with", "it", "in", "my", "country", "you", "go", "to", "jail" ], "hypothesis_tokens": [ "twenty", "years", "you", "get", "away", "with", "it", "in", "my", "country", "you", "go", "to", "jail" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 14, "reference_words": 14, "hypothesis_words": 14, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "twenty", "hypothesis": "twenty", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "years", "hypothesis": "years", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "get", "hypothesis": "get", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "away", "hypothesis": "away", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "with", "hypothesis": "with", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "it", "hypothesis": "it", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "in", "hypothesis": "in", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "country", "hypothesis": "country", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "go", "hypothesis": "go", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "jail", "hypothesis": "jail", "reference_index": 13, "hypothesis_index": 13 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.46956, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Angry", "emotion_confidence": 0.47248294949531555, "duration_seconds": 3.8740000000000236, "mos": 3.0787, "audio_variant": "original", "original_transcript_raw": "A public execution is held to constitute a cruel. ", "original_transcript": "A public execution is held to constitute a cruel.", "retranscribed_transcript": "A public execution is held to constitute a cruel.", "backend": "qwen", "emotion_analyzed_seconds": 3.874, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-002", "energy": { "value": 0.515625, "bucket": "low" }, "audio_url": "audio/utterance-002.wav", "spectrogram_url": "spectrograms/utterance-002.png", "waveform": [ 0.00693, 0.01465, 0.10003, 0.03019, 0.01927, 0.01283, 0.00556, 0.00628, 0.07286, 0.20834, 0.21464, 0.19186, 0.16564, 0.08613, 0.06141, 0.06025, 0.07544, 0.10478, 0.10029, 0.0871, 0.14052, 0.11799, 0.07303, 0.02727, 0.02044, 0.02246, 0.00968, 0.0072, 0.02644, 0.02146, 0.03546, 0.05304, 0.10622, 0.11481, 0.02945, 0.01566, 0.02794, 0.03093, 0.04326, 0.03795, 0.02114, 0.03099, 0.02352, 0.01569, 0.00633, 0.00539, 0.03874, 0.03407, 0.04674, 0.05131, 0.0596, 0.05622, 0.04278, 0.04052, 0.05454, 0.06567, 0.04876, 0.05006, 0.03707, 0.02883, 0.0455, 0.04681, 0.04839, 0.03851, 0.03133, 0.04337, 0.05065, 0.04745, 0.04082, 0.04404, 0.03971, 0.03103, 0.04185, 0.04172, 0.01478, 0.02287, 0.10209, 0.10047, 0.08521, 0.11765, 0.10578, 0.11193, 0.09132, 0.07687, 0.03434, 0.02874, 0.01534, 0.04571, 0.03227, 0.04591, 0.04451, 0.02777, 0.01772, 0.00936, 0.0076, 0.00871, 0.07082, 0.03158, 0.02078, 0.09912, 0.11909, 0.10918, 0.07818, 0.03628, 0.03247, 0.03286, 0.0285, 0.0284, 0.01408, 0.00573, 0.00555, 0.00445, 0.04676, 0.02752, 0.03907, 0.04423, 0.0358, 0.00959, 0.00916, 0.00731, 0.05906, 0.0554, 0.05416, 0.04712, 0.04289, 0.02955, 0.02084, 0.01452, 0.04704, 0.04837, 0.05333, 0.06433, 0.03698, 0.03195, 0.01809, 0.01579, 0.00899, 0.00486, 0.00634, 0.00413, 0.00475, 0.01805, 0.07046, 0.04834, 0.0165, 0.0335, 0.01771, 0.03163, 0.0643, 0.07565, 0.08275, 0.07437, 0.06383, 0.06596, 0.0444, 0.04684, 0.04893, 0.0539, 0.05221, 0.05129, 0.05467, 0.05111, 0.06104, 0.05389, 0.05278, 0.04523, 0.04333, 0.04723, 0.04725, 0.02778, 0.02815, 0.01984, 0.01672, 0.01667, 0.00886, 0.00789, 0.00822, 0.00484, 0.00568, 0.00579 ], "comparison": { "original": "A public execution is held to constitute a cruel.", "retranscribed": "A public execution is held to constitute a cruel.", "reference_tokens": [ "a", "public", "execution", "is", "held", "to", "constitute", "a", "cruel" ], "hypothesis_tokens": [ "a", "public", "execution", "is", "held", "to", "constitute", "a", "cruel" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 9, "reference_words": 9, "hypothesis_words": 9, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "public", "hypothesis": "public", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "execution", "hypothesis": "execution", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "is", "hypothesis": "is", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "held", "hypothesis": "held", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "constitute", "hypothesis": "constitute", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "cruel", "hypothesis": "cruel", "reference_index": 8, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.21464, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Angry", "emotion_confidence": 0.5610151290893555, "duration_seconds": 1.1600000000000001, "mos": 3.0894, "audio_variant": "cleaned", "original_transcript_raw": "If I swear to him. ", "original_transcript": "If I swear to him.", "retranscribed_transcript": "If I swear to him.", "backend": "qwen", "emotion_analyzed_seconds": 1.16, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-003", "energy": { "value": 0.50390625, "bucket": "low" }, "audio_url": "audio/utterance-003.wav", "spectrogram_url": "spectrograms/utterance-003.png", "waveform": [ 0.01083, 0.00981, 0.00735, 0.00995, 0.03734, 0.08286, 0.18776, 0.12687, 0.19633, 0.08647, 0.08136, 0.04551, 0.05461, 0.05298, 0.03539, 0.04053, 0.02636, 0.04429, 0.06459, 0.23464, 0.17409, 0.30202, 0.31036, 0.40695, 0.45147, 0.23902, 0.46126, 0.4427, 0.25685, 0.51318, 0.53542, 0.48384, 0.46062, 0.36043, 0.45391, 0.38662, 0.20327, 0.14511, 0.10195, 0.08328, 0.0991, 0.14109, 0.13492, 0.19101, 0.11203, 0.13119, 0.12616, 0.11741, 0.15357, 0.10883, 0.10843, 0.10931, 0.1324, 0.0815, 0.09421, 0.07644, 0.05308, 0.04116, 0.06234, 0.03569, 0.02284, 0.02336, 0.02098, 0.03515, 0.191, 0.40749, 0.46719, 0.61379, 0.47666, 0.58688, 0.61697, 0.37005, 0.63372, 0.63371, 0.62459, 0.38894, 0.60414, 0.54263, 0.30536, 0.55805, 0.53507, 0.265, 0.49687, 0.4978, 0.35891, 0.47402, 0.18525, 0.22892, 0.10998, 0.11057, 0.10029, 0.05753, 0.10084, 0.08135, 0.02613, 0.00946, 0.00861, 0.0028, 0.00242, 0.00248, 0.0012, 0.00246, 0.0748, 0.13266, 0.04866, 0.02804, 0.0228, 0.01886, 0.01544, 0.02396, 0.1452, 0.34595, 0.19963, 0.2817, 0.25476, 0.28433, 0.24696, 0.15611, 0.22444, 0.14642, 0.18721, 0.09594, 0.11402, 0.08758, 0.07123, 0.05658, 0.04449, 0.04865, 0.0753, 0.11821, 0.15328, 0.15848, 0.18145, 0.24895, 0.21567, 0.30242, 0.27478, 0.20495, 0.29669, 0.14185, 0.21113, 0.1417, 0.2212, 0.16042, 0.19362, 0.11818, 0.12372, 0.05106, 0.08782, 0.05232, 0.04471, 0.03297, 0.03951, 0.02103, 0.01221, 0.0065, 0.00832, 0.00796, 0.00615, 0.0052, 0.00419, 0.00488, 0.00633, 0.00433, 0.00428, 0.0045, 0.00539, 0.00746, 0.00559, 0.00755, 0.00615, 0.00542, 0.00497, 0.00431, 0.00351, 0.00713, 0.008, 0.00909, 0.00762, 0.0137 ], "comparison": { "original": "If I swear to him.", "retranscribed": "If I swear to him.", "reference_tokens": [ "if", "i", "swear", "to", "him" ], "hypothesis_tokens": [ "if", "i", "swear", "to", "him" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "if", "hypothesis": "if", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "swear", "hypothesis": "swear", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "him", "hypothesis": "him", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.63372, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Angry", "emotion_confidence": 0.33782458305358887, "duration_seconds": 3.2250000000000227, "mos": 3.096, "audio_variant": "cleaned", "original_transcript_raw": "It was an accident and I only heard the part about her wanting to have another baby with you. ", "original_transcript": "It was an accident and I only heard the part about her wanting to have another baby with you.", "retranscribed_transcript": "It was an accident, and I only heard the part about her wanting to have another baby with you.", "backend": "qwen", "emotion_analyzed_seconds": 3.225, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-004", "energy": { "value": 0.578125, "bucket": "medium" }, "audio_url": "audio/utterance-004.wav", "spectrogram_url": "spectrograms/utterance-004.png", "waveform": [ 0.00918, 0.06275, 0.19962, 0.24909, 0.26842, 0.25284, 0.22098, 0.09365, 0.08346, 0.18864, 0.28945, 0.31765, 0.21994, 0.12301, 0.33198, 0.33441, 0.35328, 0.29843, 0.24221, 0.2659, 0.23122, 0.16488, 0.09828, 0.0432, 0.04107, 0.06306, 0.07541, 0.06257, 0.04675, 0.05107, 0.04462, 0.0434, 0.14871, 0.18887, 0.26557, 0.25216, 0.21883, 0.0718, 0.05297, 0.04185, 0.04724, 0.12905, 0.31508, 0.32744, 0.33446, 0.26963, 0.27807, 0.29442, 0.33264, 0.31854, 0.28001, 0.21399, 0.12639, 0.13192, 0.23957, 0.29713, 0.30059, 0.1933, 0.1774, 0.24851, 0.28467, 0.28423, 0.26273, 0.24474, 0.21825, 0.10218, 0.0842, 0.06891, 0.10299, 0.22157, 0.07403, 0.03506, 0.00657, 0.04472, 0.02622, 0.26144, 0.35587, 0.3613, 0.31778, 0.29238, 0.33731, 0.34493, 0.15428, 0.08257, 0.23658, 0.10661, 0.08741, 0.30952, 0.30207, 0.32015, 0.27573, 0.29415, 0.30961, 0.2548, 0.11362, 0.13055, 0.16654, 0.25735, 0.27709, 0.24814, 0.18852, 0.17052, 0.24383, 0.29725, 0.37437, 0.30445, 0.25407, 0.1483, 0.06351, 0.07639, 0.09935, 0.1186, 0.11849, 0.23502, 0.32014, 0.2728, 0.20897, 0.23166, 0.317, 0.31706, 0.15285, 0.09769, 0.14573, 0.26976, 0.1487, 0.15343, 0.15833, 0.30563, 0.30223, 0.3291, 0.26376, 0.10064, 0.09067, 0.22188, 0.1058, 0.09206, 0.06516, 0.05389, 0.12559, 0.23614, 0.21389, 0.16661, 0.15897, 0.16617, 0.13939, 0.08223, 0.03228, 0.02823, 0.06836, 0.08965, 0.10882, 0.08742, 0.03867, 0.08346, 0.09014, 0.07551, 0.10699, 0.15087, 0.08249, 0.02835, 0.01259, 0.0163, 0.06294, 0.06254, 0.08512, 0.0874, 0.05105, 0.03247, 0.02602, 0.02241, 0.00963, 0.00584, 0.00367, 0.0025, 0.00072, 0.00068, 0.00043, 0.00482, 0.0165, 0.02538 ], "comparison": { "original": "It was an accident and I only heard the part about her wanting to have another baby with you.", "retranscribed": "It was an accident, and I only heard the part about her wanting to have another baby with you.", "reference_tokens": [ "it", "was", "an", "accident", "and", "i", "only", "heard", "the", "part", "about", "her", "wanting", "to", "have", "another", "baby", "with", "you" ], "hypothesis_tokens": [ "it", "was", "an", "accident", "and", "i", "only", "heard", "the", "part", "about", "her", "wanting", "to", "have", "another", "baby", "with", "you" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 19, "reference_words": 19, "hypothesis_words": 19, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "it", "hypothesis": "it", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "was", "hypothesis": "was", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "an", "hypothesis": "an", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "accident", "hypothesis": "accident", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "only", "hypothesis": "only", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "heard", "hypothesis": "heard", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "part", "hypothesis": "part", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "about", "hypothesis": "about", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "her", "hypothesis": "her", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "wanting", "hypothesis": "wanting", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "have", "hypothesis": "have", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "another", "hypothesis": "another", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "baby", "hypothesis": "baby", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "with", "hypothesis": "with", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 18, "hypothesis_index": 18 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.37437, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Angry", "emotion_confidence": 0.3250334560871124, "duration_seconds": 3.617999999999995, "mos": 3.0043, "audio_variant": "cleaned", "original_transcript_raw": "You're not responsible for their lives outside that classroom. ", "original_transcript": "You're not responsible for their lives outside that classroom.", "retranscribed_transcript": "You're not responsible for their lives outside that classroom.", "backend": "qwen", "emotion_analyzed_seconds": 3.618, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-005", "energy": { "value": 0.578125, "bucket": "medium" }, "audio_url": "audio/utterance-005.wav", "spectrogram_url": "spectrograms/utterance-005.png", "waveform": [ 0.01681, 0.11516, 0.18923, 0.26916, 0.39527, 0.45736, 0.46595, 0.4986, 0.50221, 0.53668, 0.48634, 0.45156, 0.48247, 0.45034, 0.40301, 0.43228, 0.34748, 0.26269, 0.2879, 0.27935, 0.20966, 0.14271, 0.09739, 0.03914, 0.0293, 0.01243, 0.04212, 0.09623, 0.17451, 0.12357, 0.11636, 0.07127, 0.13982, 0.13156, 0.1017, 0.10284, 0.04846, 0.00562, 0.00373, 0.00391, 0.0024, 0.00376, 0.12581, 0.23032, 0.32384, 0.22692, 0.22329, 0.2404, 0.21722, 0.24852, 0.30273, 0.22634, 0.24808, 0.05066, 0.1141, 0.11755, 0.08864, 0.05441, 0.11161, 0.05491, 0.04894, 0.04397, 0.04358, 0.1291, 0.10225, 0.09456, 0.05988, 0.04973, 0.02988, 0.01924, 0.02485, 0.02342, 0.04322, 0.13513, 0.0823, 0.06536, 0.14227, 0.15891, 0.15232, 0.1459, 0.13783, 0.1605, 0.26703, 0.31986, 0.3396, 0.42645, 0.45618, 0.45227, 0.41484, 0.37401, 0.34568, 0.26702, 0.2707, 0.18173, 0.20147, 0.15261, 0.16792, 0.16507, 0.16701, 0.11373, 0.10422, 0.11711, 0.08615, 0.07326, 0.0535, 0.02779, 0.04164, 0.10059, 0.20007, 0.13254, 0.07409, 0.01629, 0.00958, 0.02311, 0.10076, 0.17962, 0.29304, 0.14013, 0.17398, 0.14068, 0.16363, 0.08149, 0.06717, 0.1764, 0.13998, 0.2344, 0.15939, 0.26777, 0.25481, 0.18786, 0.34668, 0.28469, 0.18451, 0.21747, 0.19791, 0.15137, 0.11696, 0.13238, 0.06717, 0.02157, 0.12951, 0.21457, 0.20064, 0.17054, 0.17456, 0.17368, 0.17116, 0.17043, 0.0319, 0.00379, 0.00195, 0.00215, 0.15709, 0.22764, 0.0443, 0.40683, 0.22211, 0.13935, 0.16488, 0.12676, 0.14542, 0.15945, 0.1751, 0.29063, 0.18887, 0.18662, 0.1632, 0.20725, 0.14094, 0.09338, 0.07997, 0.04473, 0.02922, 0.14235, 0.10282, 0.06856, 0.09818, 0.02794, 0.02107, 0.0142 ], "comparison": { "original": "You're not responsible for their lives outside that classroom.", "retranscribed": "You're not responsible for their lives outside that classroom.", "reference_tokens": [ "youre", "not", "responsible", "for", "their", "lives", "outside", "that", "classroom" ], "hypothesis_tokens": [ "youre", "not", "responsible", "for", "their", "lives", "outside", "that", "classroom" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 9, "reference_words": 9, "hypothesis_words": 9, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "youre", "hypothesis": "youre", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "not", "hypothesis": "not", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "responsible", "hypothesis": "responsible", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "for", "hypothesis": "for", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "their", "hypothesis": "their", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "lives", "hypothesis": "lives", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "outside", "hypothesis": "outside", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "classroom", "hypothesis": "classroom", "reference_index": 8, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.53668, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Angry", "emotion_confidence": 0.36694392561912537, "duration_seconds": 1.757000000000005, "mos": 3.8506, "audio_variant": "original", "original_transcript_raw": "Done anything to hurt john. ", "original_transcript": "Done anything to hurt john.", "retranscribed_transcript": "Done anything to hurt John.", "backend": "qwen", "emotion_analyzed_seconds": 1.757, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-006", "energy": { "value": 0.5390625, "bucket": "medium" }, "audio_url": "audio/utterance-006.wav", "spectrogram_url": "spectrograms/utterance-006.png", "waveform": [ 0.08144, 0.09552, 0.03458, 0.24153, 0.21254, 0.22985, 0.25354, 0.25627, 0.24676, 0.23522, 0.19506, 0.18688, 0.18041, 0.16001, 0.14537, 0.14063, 0.08559, 0.03644, 0.03094, 0.07003, 0.03505, 0.0237, 0.02428, 0.01185, 0.10407, 0.24047, 0.25857, 0.27055, 0.27479, 0.245, 0.22448, 0.21438, 0.21299, 0.22064, 0.21566, 0.19891, 0.19841, 0.22036, 0.21753, 0.22093, 0.20187, 0.19416, 0.19022, 0.16443, 0.13044, 0.13105, 0.09456, 0.07195, 0.02394, 0.0333, 0.01779, 0.02324, 0.01547, 0.02583, 0.02583, 0.02066, 0.1822, 0.20569, 0.21208, 0.21087, 0.26239, 0.24903, 0.26121, 0.20715, 0.21548, 0.20235, 0.20123, 0.20335, 0.17133, 0.18236, 0.13964, 0.10345, 0.08515, 0.03696, 0.14053, 0.10246, 0.18968, 0.16976, 0.18779, 0.17484, 0.16718, 0.14849, 0.12262, 0.0616, 0.06974, 0.07651, 0.07951, 0.09415, 0.13711, 0.06892, 0.05447, 0.07923, 0.09487, 0.09668, 0.06406, 0.08104, 0.06203, 0.05035, 0.14694, 0.15574, 0.25226, 0.27552, 0.27333, 0.26821, 0.23385, 0.23105, 0.24887, 0.2328, 0.18737, 0.08222, 0.06087, 0.01991, 0.0217, 0.01422, 0.01838, 0.06649, 0.12006, 0.07067, 0.03685, 0.02215, 0.01938, 0.01824, 0.06274, 0.09305, 0.06249, 0.0745, 0.17793, 0.17868, 0.18266, 0.17821, 0.14456, 0.15965, 0.15102, 0.12902, 0.11281, 0.11094, 0.11424, 0.08147, 0.074, 0.07594, 0.06001, 0.06812, 0.0772, 0.08507, 0.09111, 0.08134, 0.05913, 0.07876, 0.03996, 0.07144, 0.0653, 0.05097, 0.0793, 0.06784, 0.04977, 0.01633, 0.03697, 0.07555, 0.01617, 0.02384, 0.0677, 0.02678, 0.05883, 0.02722, 0.02269, 0.02642, 0.01878, 0.01361, 0.01301, 0.00856, 0.01096, 0.01186, 0.00839, 0.01087, 0.01402, 0.00737, 0.00898, 0.01237, 0.01274, 0.01182 ], "comparison": { "original": "Done anything to hurt john.", "retranscribed": "Done anything to hurt John.", "reference_tokens": [ "done", "anything", "to", "hurt", "john" ], "hypothesis_tokens": [ "done", "anything", "to", "hurt", "john" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "done", "hypothesis": "done", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "anything", "hypothesis": "anything", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "hurt", "hypothesis": "hurt", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "john", "hypothesis": "john", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.27552, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Angry", "emotion_confidence": 0.39919063448905945, "duration_seconds": 1.603999999999985, "mos": 3.0497, "audio_variant": "original", "original_transcript_raw": "Bartenders make big bucks really", "original_transcript": "Bartenders make big bucks really", "retranscribed_transcript": "Bar tenders make big bucks.", "backend": "qwen", "emotion_analyzed_seconds": 1.604, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-007", "energy": { "value": 0.7734375, "bucket": "high" }, "audio_url": "audio/utterance-007.wav", "spectrogram_url": "spectrograms/utterance-007.png", "waveform": [ 0.00871, 0.06641, 0.01926, 0.0971, 0.10865, 0.05225, 0.10141, 0.11913, 0.11442, 0.11031, 0.10306, 0.08864, 0.08112, 0.08502, 0.08491, 0.06022, 0.02378, 0.01469, 0.00971, 0.01372, 0.00942, 0.01033, 0.03129, 0.0366, 0.01059, 0.01471, 0.11502, 0.12711, 0.13541, 0.13559, 0.10869, 0.06151, 0.06295, 0.06272, 0.06316, 0.06428, 0.08347, 0.08551, 0.09139, 0.10255, 0.10863, 0.10326, 0.08426, 0.05203, 0.04605, 0.04034, 0.04869, 0.04683, 0.02867, 0.01791, 0.00836, 0.00726, 0.03455, 0.07145, 0.0782, 0.08264, 0.07701, 0.13208, 0.13679, 0.13495, 0.1387, 0.13745, 0.12372, 0.09123, 0.06731, 0.03605, 0.02919, 0.02, 0.01989, 0.01661, 0.0118, 0.01245, 0.0117, 0.0107, 0.00787, 0.00474, 0.00656, 0.0183, 0.00529, 0.03634, 0.13483, 0.13259, 0.12837, 0.1341, 0.12994, 0.07542, 0.07385, 0.06345, 0.02881, 0.03189, 0.04068, 0.03915, 0.0343, 0.02481, 0.02505, 0.01912, 0.02128, 0.01779, 0.01297, 0.00869, 0.00692, 0.0068, 0.0069, 0.01778, 0.10676, 0.13359, 0.11557, 0.08842, 0.08387, 0.09773, 0.09135, 0.09771, 0.1056, 0.10669, 0.109, 0.10986, 0.11208, 0.10813, 0.11121, 0.11108, 0.09595, 0.11758, 0.13618, 0.08544, 0.06568, 0.02085, 0.04716, 0.03003, 0.01753, 0.01548, 0.03828, 0.074, 0.1037, 0.14023, 0.14247, 0.13339, 0.13611, 0.14332, 0.14035, 0.14183, 0.1384, 0.1318, 0.13837, 0.13863, 0.14118, 0.13353, 0.14063, 0.14106, 0.14568, 0.14188, 0.13686, 0.13745, 0.13271, 0.1281, 0.10745, 0.09591, 0.11175, 0.08797, 0.07534, 0.06985, 0.0805, 0.06611, 0.06652, 0.04501, 0.04225, 0.05215, 0.03788, 0.03912, 0.04287, 0.02225, 0.02334, 0.01726, 0.01275, 0.01709, 0.01143, 0.00913, 0.01071, 0.01061, 0.00947, 0.0073 ], "comparison": { "original": "Bartenders make big bucks really", "retranscribed": "Bar tenders make big bucks.", "reference_tokens": [ "bartenders", "make", "big", "bucks", "really" ], "hypothesis_tokens": [ "bar", "tenders", "make", "big", "bucks" ], "counts": { "substitutions": 1, "deletions": 1, "insertions": 1, "hits": 3, "reference_words": 5, "hypothesis_words": 5, "edits": 3 }, "wer": 0.6, "wer_percent": 60.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "bar", "reference_index": null, "hypothesis_index": 0 }, { "op": "substitute", "reference": "bartenders", "hypothesis": "tenders", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "make", "hypothesis": "make", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "big", "hypothesis": "big", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "bucks", "hypothesis": "bucks", "reference_index": 3, "hypothesis_index": 4 }, { "op": "delete", "reference": "really", "hypothesis": null, "reference_index": 4, "hypothesis_index": null } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.14568, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Angry", "emotion_confidence": 0.8977046012878418, "duration_seconds": 2.8840000000000146, "mos": 3.5552, "audio_variant": "cleaned", "original_transcript_raw": "The doctors are not working right now. The doctors. ", "original_transcript": "The doctors are not working right now. The doctors.", "retranscribed_transcript": "The doctors are not working right now. The doctors.", "backend": "qwen", "emotion_analyzed_seconds": 2.884, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-008", "energy": { "value": 0.828125, "bucket": "high" }, "audio_url": "audio/utterance-008.wav", "spectrogram_url": "spectrograms/utterance-008.png", "waveform": [ 0.00202, 0.04774, 0.36234, 0.49998, 0.47264, 0.05054, 0.04063, 0.02527, 0.01532, 0.00498, 0.05032, 0.13146, 0.31742, 0.46755, 0.46844, 0.43071, 0.49957, 0.43794, 0.36663, 0.32318, 0.27085, 0.1484, 0.00627, 0.00081, 0.00615, 0.00083, 0.00037, 0.00048, 0.02197, 0.18323, 0.17996, 0.15101, 0.15167, 0.14952, 0.11646, 0.08244, 0.05722, 0.03741, 0.12809, 0.26193, 0.22604, 0.21754, 0.19535, 0.11686, 0.11334, 0.10822, 0.32263, 0.43568, 0.45765, 0.43757, 0.43907, 0.38947, 0.31043, 0.22535, 0.12956, 0.01928, 0.03097, 0.02684, 0.03553, 0.1109, 0.30469, 0.45918, 0.45881, 0.37585, 0.42977, 0.42974, 0.36874, 0.16018, 0.04446, 0.01498, 0.004, 0.01468, 0.02415, 0.05073, 0.12503, 0.1671, 0.09886, 0.09374, 0.09508, 0.08526, 0.06169, 0.05737, 0.10426, 0.3834, 0.42282, 0.43756, 0.33082, 0.20737, 0.17572, 0.09504, 0.06732, 0.0271, 0.02907, 0.04334, 0.05948, 0.1399, 0.17668, 0.17622, 0.18815, 0.18073, 0.16238, 0.17192, 0.15652, 0.15198, 0.05827, 0.00671, 0.00681, 0.01277, 0.02305, 0.02105, 0.02284, 0.01723, 0.01213, 0.00664, 0.00216, 0.0016, 0.00824, 0.02403, 0.03987, 0.22673, 0.2548, 0.23271, 0.24673, 0.23915, 0.0422, 0.0373, 0.03706, 0.03191, 0.02602, 0.02035, 0.00964, 0.03379, 0.10172, 0.18723, 0.30753, 0.51175, 0.34982, 0.38619, 0.40061, 0.32555, 0.35411, 0.32741, 0.31132, 0.28857, 0.12189, 0.01723, 0.00125, 0.00134, 0.00261, 0.0003, 0.00031, 0.0003, 0.03186, 0.07784, 0.19414, 0.24912, 0.19421, 0.14727, 0.11095, 0.10085, 0.08013, 0.07732, 0.05486, 0.05327, 0.04043, 0.03351, 0.03332, 0.02102, 0.01972, 0.01499, 0.02259, 0.0151, 0.0166, 0.02045, 0.01109, 0.00331, 0.0032, 0.0013, 0.00187, 0.00243 ], "comparison": { "original": "The doctors are not working right now. The doctors.", "retranscribed": "The doctors are not working right now. The doctors.", "reference_tokens": [ "the", "doctors", "are", "not", "working", "right", "now", "the", "doctors" ], "hypothesis_tokens": [ "the", "doctors", "are", "not", "working", "right", "now", "the", "doctors" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 9, "reference_words": 9, "hypothesis_words": 9, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "doctors", "hypothesis": "doctors", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "are", "hypothesis": "are", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "not", "hypothesis": "not", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "working", "hypothesis": "working", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "right", "hypothesis": "right", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "now", "hypothesis": "now", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "doctors", "hypothesis": "doctors", "reference_index": 8, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.51175, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Angry", "emotion_confidence": 0.3986840844154358, "duration_seconds": 3.959000000000003, "mos": 3.1859, "audio_variant": "cleaned", "original_transcript_raw": "We believe that education is the practice of freedom. ", "original_transcript": "We believe that education is the practice of freedom.", "retranscribed_transcript": "We believe that education is the practice of freedom.", "backend": "qwen", "emotion_analyzed_seconds": 3.959, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-009", "energy": { "value": 0.703125, "bucket": "high" }, "audio_url": "audio/utterance-009.wav", "spectrogram_url": "spectrograms/utterance-009.png", "waveform": [ 0.01142, 0.02916, 0.04157, 0.12706, 0.28276, 0.31285, 0.34606, 0.33068, 0.33024, 0.36192, 0.37849, 0.32374, 0.02377, 0.00764, 0.10838, 0.36604, 0.34531, 0.32572, 0.20924, 0.19911, 0.21769, 0.2273, 0.26235, 0.24552, 0.25169, 0.24751, 0.2669, 0.28078, 0.25501, 0.2834, 0.29695, 0.24982, 0.06491, 0.03435, 0.03124, 0.09662, 0.2451, 0.43555, 0.55035, 0.2856, 0.06295, 0.26649, 0.14948, 0.21656, 0.33191, 0.45163, 0.51219, 0.46578, 0.20303, 0.06002, 0.09901, 0.11495, 0.09695, 0.13329, 0.13118, 0.10046, 0.03167, 0.01156, 0.06675, 0.05089, 0.12402, 0.19375, 0.18929, 0.15836, 0.15732, 0.14567, 0.14043, 0.1473, 0.09814, 0.10248, 0.11906, 0.11351, 0.11522, 0.10508, 0.18894, 0.17497, 0.15654, 0.16226, 0.13269, 0.13441, 0.11955, 0.09942, 0.06122, 0.09064, 0.10562, 0.25948, 0.36548, 0.18964, 0.07347, 0.02894, 0.0068, 0.00458, 0.02404, 0.11295, 0.37392, 0.33085, 0.20424, 0.02999, 0.0125, 0.00074, 0.02938, 0.02697, 0.01942, 0.09446, 0.3668, 0.52498, 0.51033, 0.47959, 0.44694, 0.43022, 0.48049, 0.50246, 0.34263, 0.03598, 0.00229, 0.00288, 0.00225, 0.00036, 0.03092, 0.05378, 0.14458, 0.21189, 0.1832, 0.15718, 0.12895, 0.08244, 0.04115, 0.02965, 0.06811, 0.05929, 0.05114, 0.05312, 0.12127, 0.16582, 0.19807, 0.26972, 0.20578, 0.06289, 0.04533, 0.02195, 0.01556, 0.00909, 0.00831, 0.01416, 0.02783, 0.0625, 0.10516, 0.19126, 0.21488, 0.1753, 0.1374, 0.13286, 0.13884, 0.14312, 0.15336, 0.1553, 0.08048, 0.29504, 0.28578, 0.36765, 0.31805, 0.23623, 0.19169, 0.17989, 0.08933, 0.07734, 0.04209, 0.02877, 0.01629, 0.01056, 0.00729, 0.00444, 0.0041, 0.00219, 0.00185, 0.00151, 0.00233, 0.00255, 0.0074, 0.01412 ], "comparison": { "original": "We believe that education is the practice of freedom.", "retranscribed": "We believe that education is the practice of freedom.", "reference_tokens": [ "we", "believe", "that", "education", "is", "the", "practice", "of", "freedom" ], "hypothesis_tokens": [ "we", "believe", "that", "education", "is", "the", "practice", "of", "freedom" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 9, "reference_words": 9, "hypothesis_words": 9, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "we", "hypothesis": "we", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "believe", "hypothesis": "believe", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "education", "hypothesis": "education", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "is", "hypothesis": "is", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "practice", "hypothesis": "practice", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "freedom", "hypothesis": "freedom", "reference_index": 8, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.55035, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Annoyed", "emotion_confidence": 0.3753422200679779, "duration_seconds": 0.8020000000000209, "mos": 3.2937, "audio_variant": "cleaned", "original_transcript_raw": "And there's no meat. ", "original_transcript": "And there's no meat.", "retranscribed_transcript": "And there's no meat.", "backend": "qwen", "emotion_analyzed_seconds": 0.802, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-010", "energy": { "value": 0.515625, "bucket": "low" }, "audio_url": "audio/utterance-010.wav", "spectrogram_url": "spectrograms/utterance-010.png", "waveform": [ 0.12288, 0.18806, 0.17574, 0.16423, 0.12712, 0.10177, 0.1873, 0.23265, 0.20887, 0.17601, 0.15024, 0.19695, 0.18985, 0.20071, 0.16838, 0.18659, 0.17731, 0.16302, 0.14884, 0.15157, 0.13733, 0.14593, 0.1447, 0.14664, 0.15057, 0.13621, 0.0744, 0.13507, 0.18003, 0.2315, 0.14467, 0.18854, 0.21635, 0.22345, 0.21742, 0.15848, 0.21689, 0.21823, 0.23545, 0.21412, 0.146, 0.23259, 0.22429, 0.17501, 0.14898, 0.15897, 0.15223, 0.12509, 0.09189, 0.10576, 0.10071, 0.07085, 0.10035, 0.10609, 0.09497, 0.10389, 0.09319, 0.13059, 0.08568, 0.08366, 0.08626, 0.17235, 0.21477, 0.1406, 0.06751, 0.0378, 0.0271, 0.0188, 0.02124, 0.02394, 0.02838, 0.10541, 0.12989, 0.16495, 0.17773, 0.16703, 0.11025, 0.16532, 0.18302, 0.17667, 0.16566, 0.13565, 0.15703, 0.16036, 0.15299, 0.08453, 0.15607, 0.26423, 0.19534, 0.11633, 0.20994, 0.17647, 0.11985, 0.15735, 0.12834, 0.16645, 0.15615, 0.19092, 0.16692, 0.2116, 0.23419, 0.15184, 0.25213, 0.26188, 0.25462, 0.29543, 0.17857, 0.27618, 0.25629, 0.2315, 0.19531, 0.22022, 0.17324, 0.11069, 0.09909, 0.0942, 0.08891, 0.09859, 0.0907, 0.09514, 0.079, 0.10409, 0.10179, 0.10608, 0.11139, 0.11319, 0.11354, 0.11804, 0.11705, 0.12098, 0.11454, 0.11626, 0.12598, 0.11122, 0.14054, 0.15808, 0.16794, 0.12753, 0.13681, 0.12988, 0.11143, 0.14787, 0.14593, 0.10579, 0.12351, 0.10524, 0.11122, 0.12274, 0.09152, 0.15822, 0.16289, 0.13605, 0.10278, 0.11838, 0.08351, 0.08782, 0.09585, 0.10022, 0.09421, 0.09184, 0.10796, 0.10841, 0.07933, 0.10385, 0.06642, 0.06791, 0.07026, 0.05081, 0.0509, 0.04521, 0.04336, 0.02627, 0.015, 0.01681, 0.01252, 0.01843, 0.01445, 0.01923, 0.0242, 0.0132 ], "comparison": { "original": "And there's no meat.", "retranscribed": "And there's no meat.", "reference_tokens": [ "and", "theres", "no", "meat" ], "hypothesis_tokens": [ "and", "theres", "no", "meat" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 4, "reference_words": 4, "hypothesis_words": 4, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "theres", "hypothesis": "theres", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "meat", "hypothesis": "meat", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.29543, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Annoyed", "emotion_confidence": 0.665241539478302, "duration_seconds": 2.0649999999999977, "mos": 3.1202, "audio_variant": "original", "original_transcript_raw": "Two tad two", "original_transcript": "Two tad two", "retranscribed_transcript": "Tattoo.", "backend": "qwen", "emotion_analyzed_seconds": 2.065, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-011", "energy": { "value": 0.515625, "bucket": "low" }, "audio_url": "audio/utterance-011.wav", "spectrogram_url": "spectrograms/utterance-011.png", "waveform": [ 0.06068, 0.03012, 0.02188, 0.0235, 0.01194, 0.01502, 0.01642, 0.01169, 0.15886, 0.07517, 0.05754, 0.04687, 0.05054, 0.08523, 0.13098, 0.09796, 0.08878, 0.08087, 0.06403, 0.07991, 0.04955, 0.06532, 0.0423, 0.06111, 0.0415, 0.04437, 0.04436, 0.03694, 0.03369, 0.02395, 0.02751, 0.01743, 0.01005, 0.00699, 0.00947, 0.00638, 0.00888, 0.00591, 0.00567, 0.00498, 0.00692, 0.0061, 0.0056, 0.00481, 0.00504, 0.00518, 0.00521, 0.00523, 0.00513, 0.00488, 0.0047, 0.00483, 0.00396, 0.0063, 0.00704, 0.00593, 0.00469, 0.00517, 0.00489, 0.00416, 0.00424, 0.00398, 0.00354, 0.00534, 0.00474, 0.00307, 0.00256, 0.00351, 0.00335, 0.00431, 0.00294, 0.00349, 0.00454, 0.00376, 0.0046, 0.00405, 0.00459, 0.00411, 0.00644, 0.00626, 0.0074, 0.01271, 0.01305, 0.02933, 0.0197, 0.01665, 0.01202, 0.00637, 0.00689, 0.00398, 0.00467, 0.00476, 0.00586, 0.00578, 0.00635, 0.00799, 0.01958, 0.08193, 0.09014, 0.12376, 0.13234, 0.09066, 0.09476, 0.09003, 0.08393, 0.04827, 0.05964, 0.05264, 0.07233, 0.11962, 0.10358, 0.11472, 0.04853, 0.1008, 0.07026, 0.04091, 0.02926, 0.02323, 0.0153, 0.00684, 0.00444, 0.00561, 0.00325, 0.00552, 0.00427, 0.007, 0.0036, 0.0024, 0.00429, 0.00627, 0.00321, 0.00354, 0.00433, 0.01849, 0.0213, 0.01184, 0.01576, 0.02686, 0.01628, 0.01437, 0.01606, 0.01591, 0.01081, 0.00836, 0.00567, 0.01182, 0.0165, 0.03712, 0.0604, 0.05601, 0.06471, 0.0534, 0.05183, 0.04446, 0.03943, 0.03615, 0.02954, 0.02716, 0.02929, 0.01987, 0.01103, 0.01531, 0.01261, 0.01423, 0.01201, 0.00958, 0.00803, 0.00818, 0.00478, 0.00353, 0.00705, 0.00338, 0.00374, 0.00314, 0.00446, 0.0054, 0.0055, 0.00693, 0.01062, 0.01119 ], "comparison": { "original": "Two tad two", "retranscribed": "Tattoo.", "reference_tokens": [ "two", "tad", "two" ], "hypothesis_tokens": [ "tattoo" ], "counts": { "substitutions": 1, "deletions": 2, "insertions": 0, "hits": 0, "reference_words": 3, "hypothesis_words": 1, "edits": 3 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "delete", "reference": "two", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "delete", "reference": "tad", "hypothesis": null, "reference_index": 1, "hypothesis_index": null }, { "op": "substitute", "reference": "two", "hypothesis": "tattoo", "reference_index": 2, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.15886, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Annoyed", "emotion_confidence": 0.5115674734115601, "duration_seconds": 1.3830000000000098, "mos": 3.2207, "audio_variant": "cleaned", "original_transcript_raw": "I'm sure you want your money. ", "original_transcript": "I'm sure you want your money.", "retranscribed_transcript": "I'm sure you want your money.", "backend": "qwen", "emotion_analyzed_seconds": 1.383, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-012", "energy": { "value": 0.48828125, "bucket": "low" }, "audio_url": "audio/utterance-012.wav", "spectrogram_url": "spectrograms/utterance-012.png", "waveform": [ 0.01684, 0.01204, 0.01246, 0.01527, 0.0372, 0.10226, 0.1648, 0.13389, 0.11714, 0.07832, 0.06154, 0.05235, 0.09496, 0.09762, 0.0987, 0.12966, 0.13322, 0.24173, 0.1807, 0.24803, 0.23713, 0.23765, 0.27719, 0.18011, 0.18425, 0.24938, 0.16221, 0.12075, 0.07618, 0.04324, 0.05586, 0.04929, 0.07807, 0.29373, 0.3773, 0.22078, 0.43433, 0.38178, 0.36213, 0.3309, 0.37875, 0.36294, 0.41194, 0.38826, 0.36531, 0.33802, 0.27921, 0.23657, 0.23733, 0.19096, 0.15998, 0.1758, 0.16917, 0.15942, 0.17426, 0.18076, 0.19313, 0.19179, 0.19537, 0.21092, 0.23005, 0.24268, 0.24922, 0.22645, 0.24587, 0.2623, 0.24161, 0.17943, 0.13498, 0.09871, 0.093, 0.05902, 0.06131, 0.07828, 0.10186, 0.14972, 0.23145, 0.27497, 0.3469, 0.38873, 0.4727, 0.61439, 0.5051, 0.5368, 0.48277, 0.40718, 0.27709, 0.17078, 0.12448, 0.08401, 0.05101, 0.02095, 0.01731, 0.01591, 0.00667, 0.00973, 0.06913, 0.07443, 0.07009, 0.04015, 0.09701, 0.07925, 0.2049, 0.24673, 0.22178, 0.21955, 0.255, 0.29711, 0.32989, 0.33565, 0.31144, 0.30288, 0.25348, 0.32348, 0.376, 0.34799, 0.35282, 0.32691, 0.33059, 0.31723, 0.28905, 0.26973, 0.2717, 0.25229, 0.2184, 0.21676, 0.2074, 0.19089, 0.19006, 0.21495, 0.30228, 0.32421, 0.38674, 0.3357, 0.34448, 0.31386, 0.3266, 0.30192, 0.26272, 0.24102, 0.27247, 0.31102, 0.33142, 0.37598, 0.32295, 0.28865, 0.27353, 0.25984, 0.25512, 0.25216, 0.2381, 0.25709, 0.26575, 0.2636, 0.24137, 0.22764, 0.22631, 0.20593, 0.19758, 0.18904, 0.17702, 0.15708, 0.1611, 0.13365, 0.12291, 0.12739, 0.1051, 0.10442, 0.087, 0.08258, 0.06468, 0.05949, 0.05187, 0.05392, 0.04669, 0.03775, 0.0335, 0.04042, 0.04094, 0.0523 ], "comparison": { "original": "I'm sure you want your money.", "retranscribed": "I'm sure you want your money.", "reference_tokens": [ "im", "sure", "you", "want", "your", "money" ], "hypothesis_tokens": [ "im", "sure", "you", "want", "your", "money" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 6, "reference_words": 6, "hypothesis_words": 6, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "im", "hypothesis": "im", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "sure", "hypothesis": "sure", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "want", "hypothesis": "want", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "your", "hypothesis": "your", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "money", "hypothesis": "money", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.61439, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Annoyed", "emotion_confidence": 0.2921275794506073, "duration_seconds": 9.027000000000001, "mos": 3.1823, "audio_variant": "original", "original_transcript_raw": "And then I want far. I do want far here. We're going to be busking on the streets for money. Shall we chuck far grand in at this and just start everything else out after? ", "original_transcript": "And then I want far. I do want far here. We're going to be busking on the streets for money. Shall we chuck far grand in at this and just start everything else out after?", "retranscribed_transcript": "Yeah, and then, I want far. I do want far. Yeah, Steve, we're gonna be busking on streets for money. Shall we chuck far grand in at this and just start everything else out after?", "backend": "qwen", "emotion_analyzed_seconds": 9.027, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-013", "energy": { "value": 0.578125, "bucket": "medium" }, "audio_url": "audio/utterance-013.wav", "spectrogram_url": "spectrograms/utterance-013.png", "waveform": [ 0.13019, 0.20624, 0.32512, 0.29708, 0.11171, 0.07917, 0.4843, 0.45107, 0.27822, 0.11316, 0.06873, 0.03734, 0.02393, 0.02867, 0.02091, 0.01624, 0.04821, 0.01966, 0.0363, 0.03481, 0.02761, 0.03421, 0.02683, 0.0529, 0.11378, 0.13872, 0.0684, 0.09902, 0.06472, 0.02062, 0.04575, 0.12997, 0.26331, 0.18709, 0.10106, 0.11636, 0.04776, 0.0297, 0.09001, 0.22066, 0.28759, 0.25413, 0.26471, 0.20732, 0.15855, 0.17186, 0.1115, 0.16942, 0.1197, 0.08394, 0.04404, 0.17699, 0.19126, 0.21619, 0.18987, 0.11839, 0.12341, 0.10023, 0.11015, 0.12647, 0.12301, 0.34247, 0.28306, 0.22328, 0.18468, 0.02764, 0.04691, 0.21175, 0.23936, 0.22913, 0.28103, 0.28011, 0.12623, 0.02296, 0.17307, 0.21293, 0.08963, 0.08609, 0.08521, 0.24232, 0.26804, 0.26801, 0.25332, 0.1195, 0.10662, 0.21304, 0.12384, 0.08453, 0.16025, 0.22579, 0.18655, 0.22631, 0.09374, 0.07014, 0.02881, 0.08364, 0.10301, 0.11506, 0.10208, 0.1195, 0.1203, 0.05726, 0.01735, 0.02123, 0.02588, 0.03292, 0.10591, 0.45038, 0.32482, 0.24218, 0.11529, 0.25071, 0.15256, 0.05103, 0.06946, 0.39376, 0.24044, 0.26878, 0.15653, 0.5333, 0.37645, 0.37411, 0.19965, 0.3353, 0.28387, 0.32962, 0.26726, 0.05437, 0.24971, 0.44006, 0.26254, 0.12803, 0.03789, 0.04164, 0.07327, 0.08132, 0.02185, 0.03193, 0.0808, 0.1361, 0.13858, 0.20324, 0.14716, 0.21024, 0.16906, 0.08627, 0.0494, 0.06355, 0.06256, 0.06269, 0.05247, 0.05733, 0.0577, 0.11013, 0.07789, 0.31836, 0.30988, 0.23251, 0.37405, 0.16998, 0.08644, 0.0689, 0.21701, 0.32753, 0.3711, 0.20279, 0.08988, 0.0554, 0.20412, 0.38505, 0.36516, 0.26568, 0.36683, 0.10077, 0.04618, 0.04384, 0.11973, 0.09251, 0.08762, 0.06022 ], "comparison": { "original": "And then I want far. I do want far here. We're going to be busking on the streets for money. Shall we chuck far grand in at this and just start everything else out after?", "retranscribed": "Yeah, and then, I want far. I do want far. Yeah, Steve, we're gonna be busking on streets for money. Shall we chuck far grand in at this and just start everything else out after?", "reference_tokens": [ "and", "then", "i", "want", "far", "i", "do", "want", "far", "here", "were", "going", "to", "be", "busking", "on", "the", "streets", "for", "money", "shall", "we", "chuck", "far", "grand", "in", "at", "this", "and", "just", "start", "everything", "else", "out", "after" ], "hypothesis_tokens": [ "yeah", "and", "then", "i", "want", "far", "i", "do", "want", "far", "yeah", "steve", "were", "gonna", "be", "busking", "on", "streets", "for", "money", "shall", "we", "chuck", "far", "grand", "in", "at", "this", "and", "just", "start", "everything", "else", "out", "after" ], "counts": { "substitutions": 4, "deletions": 1, "insertions": 1, "hits": 30, "reference_words": 35, "hypothesis_words": 35, "edits": 6 }, "wer": 0.17142857142857143, "wer_percent": 17.142857142857142, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "yeah", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "then", "hypothesis": "then", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "want", "hypothesis": "want", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "far", "hypothesis": "far", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "do", "hypothesis": "do", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "want", "hypothesis": "want", "reference_index": 7, "hypothesis_index": 8 }, { "op": "equal", "reference": "far", "hypothesis": "far", "reference_index": 8, "hypothesis_index": 9 }, { "op": "substitute", "reference": "here", "hypothesis": "yeah", "reference_index": 9, "hypothesis_index": 10 }, { "op": "substitute", "reference": "were", "hypothesis": "steve", "reference_index": 10, "hypothesis_index": 11 }, { "op": "substitute", "reference": "going", "hypothesis": "were", "reference_index": 11, "hypothesis_index": 12 }, { "op": "substitute", "reference": "to", "hypothesis": "gonna", "reference_index": 12, "hypothesis_index": 13 }, { "op": "equal", "reference": "be", "hypothesis": "be", "reference_index": 13, "hypothesis_index": 14 }, { "op": "equal", "reference": "busking", "hypothesis": "busking", "reference_index": 14, "hypothesis_index": 15 }, { "op": "equal", "reference": "on", "hypothesis": "on", "reference_index": 15, "hypothesis_index": 16 }, { "op": "delete", "reference": "the", "hypothesis": null, "reference_index": 16, "hypothesis_index": null }, { "op": "equal", "reference": "streets", "hypothesis": "streets", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "for", "hypothesis": "for", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "money", "hypothesis": "money", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "shall", "hypothesis": "shall", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "we", "hypothesis": "we", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "chuck", "hypothesis": "chuck", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "far", "hypothesis": "far", "reference_index": 23, "hypothesis_index": 23 }, { "op": "equal", "reference": "grand", "hypothesis": "grand", "reference_index": 24, "hypothesis_index": 24 }, { "op": "equal", "reference": "in", "hypothesis": "in", "reference_index": 25, "hypothesis_index": 25 }, { "op": "equal", "reference": "at", "hypothesis": "at", "reference_index": 26, "hypothesis_index": 26 }, { "op": "equal", "reference": "this", "hypothesis": "this", "reference_index": 27, "hypothesis_index": 27 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 28, "hypothesis_index": 28 }, { "op": "equal", "reference": "just", "hypothesis": "just", "reference_index": 29, "hypothesis_index": 29 }, { "op": "equal", "reference": "start", "hypothesis": "start", "reference_index": 30, "hypothesis_index": 30 }, { "op": "equal", "reference": "everything", "hypothesis": "everything", "reference_index": 31, "hypothesis_index": 31 }, { "op": "equal", "reference": "else", "hypothesis": "else", "reference_index": 32, "hypothesis_index": 32 }, { "op": "equal", "reference": "out", "hypothesis": "out", "reference_index": 33, "hypothesis_index": 33 }, { "op": "equal", "reference": "after", "hypothesis": "after", "reference_index": 34, "hypothesis_index": 34 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.5333, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Annoyed", "emotion_confidence": 0.5133471488952637, "duration_seconds": 6.024000000000001, "mos": 2.8212, "audio_variant": "cleaned", "original_transcript_raw": "Megan loves to treat herself, but sometimes she needs extra cash to make it happen. ", "original_transcript": "Megan loves to treat herself, but sometimes she needs extra cash to make it happen.", "retranscribed_transcript": "Megan loves to treat herself, but sometimes she needs extra cash to make it happen.", "backend": "qwen", "emotion_analyzed_seconds": 6.024, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-014", "energy": { "value": 0.5625, "bucket": "medium" }, "audio_url": "audio/utterance-014.wav", "spectrogram_url": "spectrograms/utterance-014.png", "waveform": [ 0.19003, 0.1905, 0.19577, 0.24643, 0.2423, 0.25049, 0.2198, 0.06849, 0.20737, 0.21428, 0.23782, 0.23734, 0.23004, 0.16917, 0.17229, 0.14564, 0.08315, 0.05924, 0.051, 0.18999, 0.18944, 0.19967, 0.20116, 0.2057, 0.19373, 0.19132, 0.21079, 0.27014, 0.2856, 0.27737, 0.27354, 0.17784, 0.15373, 0.15322, 0.06344, 0.07022, 0.07243, 0.05761, 0.0425, 0.02504, 0.08478, 0.19567, 0.19509, 0.06467, 0.09267, 0.09259, 0.23935, 0.23354, 0.14116, 0.02675, 0.08178, 0.14628, 0.24137, 0.22329, 0.20834, 0.08226, 0.06158, 0.29039, 0.27355, 0.25945, 0.23812, 0.16994, 0.2195, 0.02954, 0.02557, 0.01389, 0.00434, 0.00318, 0.00132, 9e-05, 6e-05, 7e-05, 6e-05, 5e-05, 5e-05, 6e-05, 6e-05, 6e-05, 4e-05, 5e-05, 5e-05, 0.0001, 0.03934, 0.2937, 0.28936, 0.28371, 0.27153, 0.28269, 0.31091, 0.29473, 0.25009, 0.26601, 0.25372, 0.06908, 0.01376, 0.02205, 0.03829, 0.03517, 0.17286, 0.28304, 0.28177, 0.25849, 0.16034, 0.16111, 0.16063, 0.11173, 0.14054, 0.25181, 0.29034, 0.26671, 0.24801, 0.23517, 0.19697, 0.18086, 0.17584, 0.12635, 0.11636, 0.0989, 0.13315, 0.19063, 0.2021, 0.2041, 0.20548, 0.21401, 0.20755, 0.17831, 0.05436, 0.0557, 0.05499, 0.25532, 0.27791, 0.26683, 0.05344, 0.09099, 0.10492, 0.04712, 0.22031, 0.20806, 0.08694, 0.00276, 0.06038, 0.10671, 0.21956, 0.24933, 0.2545, 0.25217, 0.28781, 0.23876, 0.19229, 0.08017, 0.09049, 0.08796, 0.03915, 0.06583, 0.20392, 0.14889, 0.22643, 0.25551, 0.23912, 0.15878, 0.0746, 0.24552, 0.26584, 0.13495, 0.19605, 0.26161, 0.26125, 0.30292, 0.26886, 0.01807, 0.00434, 0.23464, 0.21008, 0.14385, 0.07201, 0.06669, 0.06513, 0.04623, 0.00236, 0.00866 ], "comparison": { "original": "Megan loves to treat herself, but sometimes she needs extra cash to make it happen.", "retranscribed": "Megan loves to treat herself, but sometimes she needs extra cash to make it happen.", "reference_tokens": [ "megan", "loves", "to", "treat", "herself", "but", "sometimes", "she", "needs", "extra", "cash", "to", "make", "it", "happen" ], "hypothesis_tokens": [ "megan", "loves", "to", "treat", "herself", "but", "sometimes", "she", "needs", "extra", "cash", "to", "make", "it", "happen" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 15, "reference_words": 15, "hypothesis_words": 15, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "megan", "hypothesis": "megan", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "loves", "hypothesis": "loves", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "treat", "hypothesis": "treat", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "herself", "hypothesis": "herself", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "but", "hypothesis": "but", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "sometimes", "hypothesis": "sometimes", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "she", "hypothesis": "she", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "needs", "hypothesis": "needs", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "extra", "hypothesis": "extra", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "cash", "hypothesis": "cash", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "make", "hypothesis": "make", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "it", "hypothesis": "it", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "happen", "hypothesis": "happen", "reference_index": 14, "hypothesis_index": 14 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.31091, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Annoyed", "emotion_confidence": 0.5677075386047363, "duration_seconds": 1.024000000000001, "mos": 3.4309, "audio_variant": "cleaned", "original_transcript_raw": "He's in for a world of hurt. ", "original_transcript": "He's in for a world of hurt.", "retranscribed_transcript": "He's in for a world of hurt.", "backend": "qwen", "emotion_analyzed_seconds": 1.024, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-015", "energy": { "value": 0.5703125, "bucket": "medium" }, "audio_url": "audio/utterance-015.wav", "spectrogram_url": "spectrograms/utterance-015.png", "waveform": [ 0.02086, 0.02257, 0.0388, 0.07933, 0.11079, 0.07764, 0.08415, 0.18042, 0.1093, 0.17535, 0.10842, 0.13098, 0.11301, 0.12501, 0.10975, 0.11996, 0.13335, 0.14302, 0.13917, 0.21201, 0.28065, 0.22455, 0.35989, 0.27731, 0.12998, 0.25809, 0.22738, 0.18569, 0.21118, 0.21313, 0.23703, 0.22237, 0.12118, 0.18801, 0.14435, 0.11553, 0.11825, 0.05502, 0.10525, 0.07944, 0.10269, 0.08694, 0.08819, 0.05698, 0.03652, 0.10069, 0.04754, 0.05247, 0.03776, 0.03559, 0.02579, 0.03328, 0.05378, 0.16185, 0.06007, 0.19559, 0.20327, 0.13864, 0.16521, 0.07267, 0.17586, 0.08053, 0.2138, 0.17524, 0.18187, 0.16606, 0.11854, 0.16942, 0.11869, 0.18207, 0.06417, 0.1442, 0.07173, 0.10985, 0.10705, 0.08728, 0.09628, 0.05451, 0.10028, 0.06454, 0.10207, 0.10424, 0.11049, 0.12935, 0.0772, 0.13553, 0.06844, 0.14982, 0.1634, 0.13823, 0.18755, 0.08962, 0.22463, 0.21597, 0.17586, 0.19501, 0.13527, 0.18957, 0.1955, 0.11764, 0.20618, 0.22779, 0.11109, 0.22782, 0.21793, 0.2047, 0.21376, 0.12726, 0.2154, 0.21282, 0.17081, 0.23513, 0.11756, 0.23727, 0.21976, 0.15803, 0.21657, 0.19206, 0.17045, 0.1563, 0.09433, 0.05274, 0.07998, 0.10288, 0.07732, 0.12468, 0.09351, 0.10665, 0.12054, 0.1276, 0.09728, 0.14325, 0.10515, 0.18999, 0.05783, 0.12291, 0.09041, 0.11916, 0.09535, 0.15055, 0.0825, 0.12994, 0.08998, 0.15867, 0.14999, 0.20844, 0.23131, 0.19007, 0.19583, 0.17508, 0.12804, 0.17554, 0.17168, 0.17726, 0.21005, 0.12854, 0.22588, 0.19683, 0.08302, 0.18391, 0.08042, 0.15793, 0.15461, 0.16595, 0.10395, 0.06255, 0.08028, 0.0316, 0.08871, 0.116, 0.01592, 0.00818, 0.0377, 0.01599, 0.00721, 0.00905, 0.00832, 0.0153, 0.01961, 0.02093 ], "comparison": { "original": "He's in for a world of hurt.", "retranscribed": "He's in for a world of hurt.", "reference_tokens": [ "hes", "in", "for", "a", "world", "of", "hurt" ], "hypothesis_tokens": [ "hes", "in", "for", "a", "world", "of", "hurt" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 7, "reference_words": 7, "hypothesis_words": 7, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "hes", "hypothesis": "hes", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "in", "hypothesis": "in", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "for", "hypothesis": "for", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "world", "hypothesis": "world", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "hurt", "hypothesis": "hurt", "reference_index": 6, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.35989, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Annoyed", "emotion_confidence": 0.3533565402030945, "duration_seconds": 1.0410000000000004, "mos": 2.9578, "audio_variant": "cleaned", "original_transcript_raw": "माँ है ना? ", "original_transcript": "माँ है ना?", "retranscribed_transcript": "My hair now.", "backend": "qwen", "emotion_analyzed_seconds": 1.041, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-016", "energy": { "value": 0.60546875, "bucket": "high" }, "audio_url": "audio/utterance-016.wav", "spectrogram_url": "spectrograms/utterance-016.png", "waveform": [ 0.25649, 0.23731, 0.24191, 0.1967, 0.19635, 0.18112, 0.18572, 0.19104, 0.16387, 0.15471, 0.16941, 0.16902, 0.1672, 0.19607, 0.37275, 0.53053, 0.5585, 0.46181, 0.52536, 0.52186, 0.49558, 0.59866, 0.57718, 0.52264, 0.5796, 0.5742, 0.57971, 0.53861, 0.4318, 0.44374, 0.44247, 0.46856, 0.47515, 0.42067, 0.45706, 0.42641, 0.38841, 0.42759, 0.43459, 0.42006, 0.40512, 0.33966, 0.31496, 0.28478, 0.24347, 0.15728, 0.14513, 0.1382, 0.11275, 0.09841, 0.10334, 0.09311, 0.08944, 0.08098, 0.06785, 0.07682, 0.06007, 0.07766, 0.09551, 0.10381, 0.11813, 0.13086, 0.13672, 0.17095, 0.17661, 0.20271, 0.26279, 0.22993, 0.29767, 0.29732, 0.35213, 0.37807, 0.40162, 0.41939, 0.38912, 0.41756, 0.41704, 0.41668, 0.42052, 0.3877, 0.38655, 0.38559, 0.41522, 0.51462, 0.53974, 0.45196, 0.39622, 0.41692, 0.38899, 0.38076, 0.34242, 0.40128, 0.36255, 0.25996, 0.19661, 0.13895, 0.16462, 0.15683, 0.1537, 0.15794, 0.14777, 0.15255, 0.14513, 0.1491, 0.15528, 0.15971, 0.15698, 0.15538, 0.21485, 0.27109, 0.37161, 0.44884, 0.40816, 0.42171, 0.48881, 0.4178, 0.42414, 0.31364, 0.29363, 0.28924, 0.29927, 0.26424, 0.24147, 0.24332, 0.23692, 0.24223, 0.2428, 0.23627, 0.21034, 0.21884, 0.22318, 0.19625, 0.19023, 0.18541, 0.16328, 0.1669, 0.1589, 0.16285, 0.14994, 0.13193, 0.11351, 0.10807, 0.11068, 0.1104, 0.06946, 0.08873, 0.07596, 0.06899, 0.05609, 0.05326, 0.0519, 0.04745, 0.03863, 0.03187, 0.0264, 0.01871, 0.01126, 0.00634, 0.0047, 0.00298, 0.00153, 0.00057, 0.00044, 0.00039, 0.00033, 0.00026, 0.00024, 0.00018, 0.00021, 0.00017, 0.00012, 0.00456, 0.00794, 0.01338, 0.03053, 0.03135, 0.05383, 0.0432, 0.04244, 0.05148 ], "comparison": { "original": "माँ है ना?", "retranscribed": "My hair now.", "reference_tokens": [ "माँ", "है", "ना" ], "hypothesis_tokens": [ "my", "hair", "now" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 0, "hits": 0, "reference_words": 3, "hypothesis_words": 3, "edits": 3 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "substitute", "reference": "माँ", "hypothesis": "my", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "है", "hypothesis": "hair", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "ना", "hypothesis": "now", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.59866, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Annoyed", "emotion_confidence": 0.46658822894096375, "duration_seconds": 3.7379999999999995, "mos": 2.8945, "audio_variant": "cleaned", "original_transcript_raw": "han't holding on no everything's great", "original_transcript": "han't holding on no everything's great", "retranscribed_transcript": "Can't holding on. No, everything's great.", "backend": "qwen", "emotion_analyzed_seconds": 3.738, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-017", "energy": { "value": 0.63671875, "bucket": "high" }, "audio_url": "audio/utterance-017.wav", "spectrogram_url": "spectrograms/utterance-017.png", "waveform": [ 0.09798, 0.06719, 0.02142, 0.00189, 0.00148, 0.0022, 0.00074, 0.00144, 0.00177, 0.00124, 0.00096, 0.00132, 0.00206, 0.00268, 0.00642, 0.01358, 0.03432, 0.03204, 0.0446, 0.1351, 0.23521, 0.27401, 0.31037, 0.29055, 0.23173, 0.22021, 0.24379, 0.24922, 0.323, 0.39761, 0.3904, 0.22985, 0.13377, 0.06626, 0.01862, 0.01143, 0.00442, 0.00197, 0.03455, 0.09509, 0.11528, 0.08529, 0.08805, 0.07326, 0.06014, 0.02746, 0.01073, 0.00342, 0.0017, 0.00109, 0.00171, 0.00066, 0.00089, 0.00104, 0.00107, 0.00135, 0.00096, 0.00162, 0.00249, 0.03177, 0.38459, 0.28271, 0.07355, 0.02747, 0.0137, 0.13478, 0.18477, 0.17362, 0.14766, 0.17041, 0.13167, 0.08945, 0.09949, 0.09799, 0.20276, 0.21972, 0.20156, 0.26734, 0.25892, 0.15343, 0.12637, 0.08222, 0.05532, 0.04941, 0.02274, 0.01414, 0.01155, 0.00671, 0.00901, 0.00453, 0.00281, 0.00246, 0.00206, 0.00102, 0.00072, 0.00079, 0.00074, 0.00091, 0.00087, 0.00073, 0.00069, 0.00079, 0.00077, 0.00104, 0.00082, 0.00074, 0.00074, 0.0009, 0.00054, 0.00063, 0.00054, 0.00062, 0.00047, 0.0007, 0.00104, 0.05896, 0.10748, 0.19262, 0.38353, 0.36449, 0.36311, 0.40878, 0.43919, 0.44508, 0.35568, 0.30785, 0.23178, 0.20551, 0.11507, 0.07797, 0.04556, 0.02137, 0.00626, 0.00108, 0.00242, 0.2032, 0.30881, 0.32461, 0.12846, 0.16572, 0.21485, 0.18874, 0.13068, 0.06653, 0.01082, 0.01837, 0.01707, 0.20584, 0.19468, 0.16844, 0.12672, 0.06435, 0.10424, 0.07896, 0.00787, 0.00199, 0.02677, 0.17444, 0.33684, 0.43731, 0.30971, 0.28803, 0.15707, 0.12964, 0.13251, 0.03505, 0.01209, 0.00368, 0.00141, 0.01965, 0.03363, 0.05146, 0.05278, 0.05757, 0.03718, 0.01764, 0.00749, 0.02283, 0.05898, 0.07869 ], "comparison": { "original": "han't holding on no everything's great", "retranscribed": "Can't holding on. No, everything's great.", "reference_tokens": [ "hant", "holding", "on", "no", "everythings", "great" ], "hypothesis_tokens": [ "cant", "holding", "on", "no", "everythings", "great" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 6, "hypothesis_words": 6, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "substitute", "reference": "hant", "hypothesis": "cant", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "holding", "hypothesis": "holding", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "on", "hypothesis": "on", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "everythings", "hypothesis": "everythings", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "great", "hypothesis": "great", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.44508, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Annoyed", "emotion_confidence": 0.4270736873149872, "duration_seconds": 13.156999999999982, "mos": 3.2729, "audio_variant": "original", "original_transcript_raw": "Daddy please why don't we go somewhere and talk this out in a nice reasonable environment somewhere safe in front of a lot of witnesses and just sit down and talk? ", "original_transcript": "Daddy please why don't we go somewhere and talk this out in a nice reasonable environment somewhere safe in front of a lot of witnesses and just sit down and talk?", "retranscribed_transcript": "Daddy, please. Um, why don't why don't we go somewhere and talk this out? In a nice, reasonable environment, somewhere safe in front of a lot of witnesses, and just sit down and talk.", "backend": "qwen", "emotion_analyzed_seconds": 13.157, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-018", "energy": { "value": 0.76953125, "bucket": "high" }, "audio_url": "audio/utterance-018.wav", "spectrogram_url": "spectrograms/utterance-018.png", "waveform": [ 0.44155, 0.09843, 0.53427, 0.50555, 0.11316, 0.1064, 0.06488, 0.18904, 0.22818, 0.16948, 0.11245, 0.12508, 0.34957, 0.54959, 0.37384, 0.10106, 0.09942, 0.14401, 0.1017, 0.15152, 0.23011, 0.30097, 0.27707, 0.39829, 0.26731, 0.25877, 0.45689, 0.28372, 0.39079, 0.37425, 0.4228, 0.2683, 0.25088, 0.27252, 0.20671, 0.19811, 0.22212, 0.1359, 0.18014, 0.17161, 0.39536, 0.30512, 0.26057, 0.15843, 0.39614, 0.40999, 0.33744, 0.29047, 0.06535, 0.25523, 0.30352, 0.21641, 0.20769, 0.21728, 0.35941, 0.10791, 0.17796, 0.40118, 0.12874, 0.09324, 0.08297, 0.10665, 0.43218, 0.13889, 0.12252, 0.31939, 0.37129, 0.36468, 0.22428, 0.05522, 0.0327, 0.01581, 0.01357, 0.56834, 0.50359, 0.1859, 0.43038, 0.39768, 0.02416, 0.17016, 0.26665, 0.16736, 0.04235, 0.27544, 0.1817, 0.24106, 0.56334, 0.43886, 0.33845, 0.05641, 0.0333, 0.16747, 0.21453, 0.11658, 0.49172, 0.34317, 0.33854, 0.29917, 0.12244, 0.24409, 0.24499, 0.23241, 0.10894, 0.23214, 0.29658, 0.28585, 0.35106, 0.64556, 0.25289, 0.11849, 0.09135, 0.02377, 0.05844, 0.34198, 0.32799, 0.19595, 0.14179, 0.32456, 0.27161, 0.29981, 0.3642, 0.36636, 0.16302, 0.26997, 0.41267, 0.46487, 0.08935, 0.04998, 0.00808, 0.07163, 0.16461, 0.18391, 0.18935, 0.2372, 0.36592, 0.16377, 0.15005, 0.12935, 0.33138, 0.37287, 0.17017, 0.1722, 0.17279, 0.14459, 0.0287, 0.23697, 0.29144, 0.24773, 0.23518, 0.27975, 0.33863, 0.42137, 0.10087, 0.34931, 0.4264, 0.08948, 0.17153, 0.15068, 0.18952, 0.18207, 0.14155, 0.06825, 0.35183, 0.47444, 0.22833, 0.42185, 0.3772, 0.21358, 0.31719, 0.36685, 0.35105, 0.37159, 0.23225, 0.40704, 0.44685, 0.40575, 0.40866, 0.14718, 0.13446, 0.09882 ], "comparison": { "original": "Daddy please why don't we go somewhere and talk this out in a nice reasonable environment somewhere safe in front of a lot of witnesses and just sit down and talk?", "retranscribed": "Daddy, please. Um, why don't why don't we go somewhere and talk this out? In a nice, reasonable environment, somewhere safe in front of a lot of witnesses, and just sit down and talk.", "reference_tokens": [ "daddy", "please", "why", "dont", "we", "go", "somewhere", "and", "talk", "this", "out", "in", "a", "nice", "reasonable", "environment", "somewhere", "safe", "in", "front", "of", "a", "lot", "of", "witnesses", "and", "just", "sit", "down", "and", "talk" ], "hypothesis_tokens": [ "daddy", "please", "um", "why", "dont", "why", "dont", "we", "go", "somewhere", "and", "talk", "this", "out", "in", "a", "nice", "reasonable", "environment", "somewhere", "safe", "in", "front", "of", "a", "lot", "of", "witnesses", "and", "just", "sit", "down", "and", "talk" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 3, "hits": 31, "reference_words": 31, "hypothesis_words": 34, "edits": 3 }, "wer": 0.0967741935483871, "wer_percent": 9.67741935483871, "alignment": [ { "op": "equal", "reference": "daddy", "hypothesis": "daddy", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "please", "hypothesis": "please", "reference_index": 1, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "um", "reference_index": null, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "why", "reference_index": null, "hypothesis_index": 3 }, { "op": "insert", "reference": null, "hypothesis": "dont", "reference_index": null, "hypothesis_index": 4 }, { "op": "equal", "reference": "why", "hypothesis": "why", "reference_index": 2, "hypothesis_index": 5 }, { "op": "equal", "reference": "dont", "hypothesis": "dont", "reference_index": 3, "hypothesis_index": 6 }, { "op": "equal", "reference": "we", "hypothesis": "we", "reference_index": 4, "hypothesis_index": 7 }, { "op": "equal", "reference": "go", "hypothesis": "go", "reference_index": 5, "hypothesis_index": 8 }, { "op": "equal", "reference": "somewhere", "hypothesis": "somewhere", "reference_index": 6, "hypothesis_index": 9 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 7, "hypothesis_index": 10 }, { "op": "equal", "reference": "talk", "hypothesis": "talk", "reference_index": 8, "hypothesis_index": 11 }, { "op": "equal", "reference": "this", "hypothesis": "this", "reference_index": 9, "hypothesis_index": 12 }, { "op": "equal", "reference": "out", "hypothesis": "out", "reference_index": 10, "hypothesis_index": 13 }, { "op": "equal", "reference": "in", "hypothesis": "in", "reference_index": 11, "hypothesis_index": 14 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 12, "hypothesis_index": 15 }, { "op": "equal", "reference": "nice", "hypothesis": "nice", "reference_index": 13, "hypothesis_index": 16 }, { "op": "equal", "reference": "reasonable", "hypothesis": "reasonable", "reference_index": 14, "hypothesis_index": 17 }, { "op": "equal", "reference": "environment", "hypothesis": "environment", "reference_index": 15, "hypothesis_index": 18 }, { "op": "equal", "reference": "somewhere", "hypothesis": "somewhere", "reference_index": 16, "hypothesis_index": 19 }, { "op": "equal", "reference": "safe", "hypothesis": "safe", "reference_index": 17, "hypothesis_index": 20 }, { "op": "equal", "reference": "in", "hypothesis": "in", "reference_index": 18, "hypothesis_index": 21 }, { "op": "equal", "reference": "front", "hypothesis": "front", "reference_index": 19, "hypothesis_index": 22 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 20, "hypothesis_index": 23 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 21, "hypothesis_index": 24 }, { "op": "equal", "reference": "lot", "hypothesis": "lot", "reference_index": 22, "hypothesis_index": 25 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 23, "hypothesis_index": 26 }, { "op": "equal", "reference": "witnesses", "hypothesis": "witnesses", "reference_index": 24, "hypothesis_index": 27 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 25, "hypothesis_index": 28 }, { "op": "equal", "reference": "just", "hypothesis": "just", "reference_index": 26, "hypothesis_index": 29 }, { "op": "equal", "reference": "sit", "hypothesis": "sit", "reference_index": 27, "hypothesis_index": 30 }, { "op": "equal", "reference": "down", "hypothesis": "down", "reference_index": 28, "hypothesis_index": 31 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 29, "hypothesis_index": 32 }, { "op": "equal", "reference": "talk", "hypothesis": "talk", "reference_index": 30, "hypothesis_index": 33 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.64556, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Disgusted", "emotion_confidence": 0.3339928686618805, "duration_seconds": 1.6549999999999727, "mos": 2.8264, "audio_variant": "cleaned", "original_transcript_raw": "Lucy loves to get away. ", "original_transcript": "Lucy loves to get away.", "retranscribed_transcript": "Lucy loves to get away.", "backend": "qwen", "emotion_analyzed_seconds": 1.655, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-019", "energy": { "value": 0.515625, "bucket": "low" }, "audio_url": "audio/utterance-019.wav", "spectrogram_url": "spectrograms/utterance-019.png", "waveform": [ 0.19105, 0.13576, 0.13049, 0.14771, 0.17175, 0.20172, 0.21152, 0.21223, 0.20574, 0.2002, 0.2023, 0.18729, 0.1532, 0.09047, 0.0612, 0.07509, 0.04871, 0.04092, 0.0353, 0.02881, 0.02908, 0.02996, 0.02728, 0.04121, 0.06961, 0.19984, 0.25343, 0.2868, 0.301, 0.31963, 0.3187, 0.29985, 0.29039, 0.28976, 0.29841, 0.32698, 0.33897, 0.27713, 0.27346, 0.27045, 0.25877, 0.24825, 0.25056, 0.23852, 0.22329, 0.2218, 0.2092, 0.20395, 0.20086, 0.19658, 0.21759, 0.21213, 0.23452, 0.26044, 0.23638, 0.2793, 0.26959, 0.26343, 0.2519, 0.27485, 0.22932, 0.20912, 0.21858, 0.22079, 0.22457, 0.2146, 0.21981, 0.22079, 0.20019, 0.15839, 0.15733, 0.15354, 0.14114, 0.12159, 0.11644, 0.09988, 0.10261, 0.08803, 0.07415, 0.07345, 0.07613, 0.06096, 0.05778, 0.04875, 0.04158, 0.05352, 0.07249, 0.07217, 0.06973, 0.04065, 0.04999, 0.05028, 0.04486, 0.02725, 0.00248, 0.00116, 0.00114, 0.03491, 0.07093, 0.05433, 0.13148, 0.17777, 0.18784, 0.13952, 0.07559, 0.05675, 0.04228, 0.03591, 0.05245, 0.11365, 0.20848, 0.28455, 0.36454, 0.23336, 0.2188, 0.20497, 0.23474, 0.22944, 0.27603, 0.28266, 0.22657, 0.21347, 0.2272, 0.25889, 0.24934, 0.20433, 0.25986, 0.26396, 0.28095, 0.24242, 0.24916, 0.23575, 0.24845, 0.27127, 0.32367, 0.33934, 0.26541, 0.21799, 0.19911, 0.23296, 0.21855, 0.30053, 0.2742, 0.19401, 0.26033, 0.26811, 0.274, 0.23822, 0.23485, 0.22328, 0.22215, 0.21936, 0.215, 0.17199, 0.13866, 0.1371, 0.15861, 0.15824, 0.18099, 0.20575, 0.18207, 0.18961, 0.18412, 0.17133, 0.17716, 0.17133, 0.16616, 0.12544, 0.11019, 0.07132, 0.07374, 0.05095, 0.05162, 0.0396, 0.03703, 0.01685, 0.01442, 0.01444, 0.01335, 0.01644 ], "comparison": { "original": "Lucy loves to get away.", "retranscribed": "Lucy loves to get away.", "reference_tokens": [ "lucy", "loves", "to", "get", "away" ], "hypothesis_tokens": [ "lucy", "loves", "to", "get", "away" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "lucy", "hypothesis": "lucy", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "loves", "hypothesis": "loves", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "get", "hypothesis": "get", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "away", "hypothesis": "away", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.36454, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Disgusted", "emotion_confidence": 0.28761351108551025, "duration_seconds": 2.5600000000000023, "mos": 3.5122, "audio_variant": "cleaned", "original_transcript_raw": "It's munch. ", "original_transcript": "It's munch.", "retranscribed_transcript": "It's munch.", "backend": "qwen", "emotion_analyzed_seconds": 2.56, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-020", "energy": { "value": 0.384765625, "bucket": "low" }, "audio_url": "audio/utterance-020.wav", "spectrogram_url": "spectrograms/utterance-020.png", "waveform": [ 0.08854, 0.06049, 0.02962, 0.01142, 0.00088, 0.00113, 0.00059, 0.00075, 0.00092, 0.00096, 0.00099, 0.00092, 0.00096, 0.00075, 0.001, 0.00103, 0.00068, 0.00069, 0.00087, 0.00074, 0.0008, 0.00051, 0.00068, 0.00054, 0.00065, 0.00065, 0.00043, 0.00041, 0.00058, 0.00067, 0.00044, 0.00045, 0.0003, 0.00038, 0.0004, 0.00024, 0.00027, 0.00018, 0.00018, 5e-05, 8e-05, 7e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 1e-05, 2e-05, 2e-05, 3e-05, 1e-05, 1e-05, 1e-05, 2e-05, 2e-05, 2e-05, 2e-05, 1e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 1e-05, 2e-05, 1e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 3e-05, 5e-05, 6e-05, 0.00017, 0.00019, 0.00028, 0.00106, 0.00077, 0.00106, 0.00061, 0.00084, 0.00088, 0.00082, 0.00106, 0.05408, 0.01116, 0.01466, 0.01502, 0.01222, 0.01524, 0.01537, 0.02184, 0.02052, 0.01901, 0.01759, 0.02069, 0.01368, 0.01775, 0.01629, 0.01331, 0.01379, 0.00809, 0.00839, 0.00635, 0.00465, 0.00437, 0.00372, 0.00401, 0.00147, 0.00218, 0.00249, 0.00129, 0.00194, 0.00278, 0.00149, 0.00247, 0.00251, 0.16553, 0.32284, 0.21222, 0.04827, 0.00767, 0.00711, 0.01547, 0.0333, 0.071, 0.08633, 0.04326, 0.03072, 0.00803, 0.00796, 0.0534, 0.21411, 0.23764, 0.18473, 0.19107, 0.16249, 0.1594, 0.13805, 0.1132, 0.07967, 0.08648, 0.08659, 0.06946, 0.04893, 0.02242, 0.01134, 0.16507, 0.07852, 0.1353, 0.14559, 0.12523, 0.16011, 0.15049, 0.12311, 0.14731, 0.13806, 0.05665, 0.0393, 0.02053, 0.0116, 0.01037, 0.00451, 0.00262, 0.00227, 0.00214, 0.0023, 0.00329, 0.00256, 0.00186, 0.00243, 0.01048, 0.01865, 0.03298, 0.02291 ], "comparison": { "original": "It's munch.", "retranscribed": "It's munch.", "reference_tokens": [ "its", "munch" ], "hypothesis_tokens": [ "its", "munch" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 2, "hypothesis_words": 2, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "its", "hypothesis": "its", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "munch", "hypothesis": "munch", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.32284, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Disgusted", "emotion_confidence": 0.4473888576030731, "duration_seconds": 2.269999999999982, "mos": 2.9429, "audio_variant": "cleaned", "original_transcript_raw": "mh. ", "original_transcript": "mh.", "retranscribed_transcript": "Mmm, mmm.", "backend": "qwen", "emotion_analyzed_seconds": 2.27, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-021", "energy": { "value": 0.435546875, "bucket": "low" }, "audio_url": "audio/utterance-021.wav", "spectrogram_url": "spectrograms/utterance-021.png", "waveform": [ 0.06624, 0.06351, 0.09763, 0.10413, 0.11462, 0.12881, 0.12163, 0.12148, 0.12327, 0.13199, 0.13682, 0.15527, 0.14067, 0.14622, 0.16053, 0.15717, 0.15765, 0.14864, 0.18236, 0.17036, 0.14385, 0.14843, 0.14635, 0.1413, 0.15047, 0.15862, 0.15132, 0.15293, 0.15324, 0.15985, 0.1672, 0.16621, 0.17097, 0.18177, 0.18678, 0.1883, 0.18214, 0.17651, 0.18142, 0.18095, 0.17245, 0.19181, 0.19206, 0.19966, 0.18659, 0.17484, 0.16946, 0.15345, 0.14858, 0.13861, 0.136, 0.1259, 0.12487, 0.11638, 0.108, 0.09499, 0.09891, 0.10232, 0.10568, 0.10951, 0.10538, 0.1072, 0.09025, 0.06985, 0.06983, 0.06188, 0.06003, 0.06256, 0.06732, 0.06093, 0.05757, 0.05614, 0.06541, 0.02678, 0.01177, 0.00836, 0.00123, 0.00087, 0.0004, 0.00036, 0.00022, 0.00021, 0.00017, 0.00019, 0.00014, 0.00013, 0.0001, 9e-05, 8e-05, 7e-05, 7e-05, 6e-05, 5e-05, 5e-05, 6e-05, 6e-05, 0.00038, 0.00737, 0.02916, 0.05187, 0.0669, 0.07905, 0.08731, 0.10301, 0.1056, 0.12457, 0.12982, 0.13164, 0.15431, 0.16321, 0.16169, 0.15964, 0.15743, 0.13899, 0.1313, 0.14309, 0.14756, 0.14677, 0.1492, 0.13616, 0.12909, 0.14528, 0.14599, 0.15727, 0.14445, 0.11441, 0.12559, 0.12208, 0.11361, 0.10409, 0.10781, 0.1104, 0.11654, 0.11791, 0.13004, 0.1505, 0.15644, 0.16771, 0.15814, 0.16461, 0.15213, 0.15435, 0.15042, 0.15159, 0.15249, 0.14998, 0.14921, 0.14466, 0.15218, 0.15468, 0.14914, 0.13104, 0.12353, 0.11953, 0.1036, 0.09863, 0.08894, 0.09165, 0.09227, 0.08486, 0.08284, 0.07927, 0.07534, 0.07059, 0.05661, 0.06481, 0.03089, 0.01791, 0.00348, 0.00139, 0.0003, 0.00018, 0.0001, 0.0001, 0.00021, 0.00029, 0.00143, 0.00366, 0.00511, 0.00731 ], "comparison": { "original": "mh.", "retranscribed": "Mmm, mmm.", "reference_tokens": [ "mh" ], "hypothesis_tokens": [ "mmm", "mmm" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 1, "hits": 0, "reference_words": 1, "hypothesis_words": 2, "edits": 2 }, "wer": 2.0, "wer_percent": 200.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "mmm", "reference_index": null, "hypothesis_index": 0 }, { "op": "substitute", "reference": "mh", "hypothesis": "mmm", "reference_index": 0, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.19966, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Disgusted", "emotion_confidence": 0.7178391814231873, "duration_seconds": 0.8199999999999932, "mos": 3.0698, "audio_variant": "original", "original_transcript_raw": "Gross that", "original_transcript": "Gross that", "retranscribed_transcript": "Gross.", "backend": "qwen", "emotion_analyzed_seconds": 0.82, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-022", "energy": { "value": 0.578125, "bucket": "medium" }, "audio_url": "audio/utterance-022.wav", "spectrogram_url": "spectrograms/utterance-022.png", "waveform": [ 0.02507, 0.03915, 0.02425, 0.02952, 0.02413, 0.03053, 0.028, 0.02513, 0.03305, 0.02266, 0.02858, 0.03159, 0.06869, 0.0894, 0.1655, 0.30158, 0.24082, 0.36794, 0.30543, 0.40221, 0.52328, 0.30159, 0.53449, 0.29309, 0.56156, 0.51512, 0.60211, 0.56359, 0.29653, 0.49472, 0.29369, 0.49886, 0.26274, 0.48693, 0.20819, 0.42323, 0.41475, 0.41196, 0.28364, 0.2844, 0.2643, 0.33747, 0.31529, 0.32995, 0.26508, 0.25527, 0.25285, 0.21224, 0.26584, 0.22839, 0.10853, 0.15251, 0.07087, 0.08017, 0.09075, 0.07597, 0.05296, 0.07514, 0.08945, 0.0696, 0.10535, 0.09514, 0.11105, 0.17259, 0.29034, 0.24791, 0.36082, 0.31185, 0.31266, 0.39541, 0.45293, 0.4703, 0.41999, 0.38155, 0.46569, 0.36827, 0.30942, 0.32633, 0.32716, 0.34719, 0.28343, 0.32182, 0.25293, 0.21566, 0.23115, 0.2368, 0.18031, 0.13304, 0.152, 0.1094, 0.09816, 0.09557, 0.07748, 0.0744, 0.09398, 0.07858, 0.05582, 0.07533, 0.05827, 0.04143, 0.03743, 0.0331, 0.03063, 0.0328, 0.02388, 0.02006, 0.02185, 0.03033, 0.03383, 0.03202, 0.02414, 0.03454, 0.0321, 0.02543, 0.02593, 0.03451, 0.03659, 0.03386, 0.04706, 0.03048, 0.02312, 0.04018, 0.04141, 0.02046, 0.02795, 0.03726, 0.03778, 0.03609, 0.05599, 0.04605, 0.04523, 0.06705, 0.09211, 0.12599, 0.10537, 0.11328, 0.05966, 0.11546, 0.04629, 0.1049, 0.10744, 0.1682, 0.12374, 0.07444, 0.14916, 0.11232, 0.13199, 0.06728, 0.08864, 0.09425, 0.08489, 0.14628, 0.15735, 0.15959, 0.09387, 0.16088, 0.11133, 0.29147, 0.07438, 0.29179, 0.08548, 0.08115, 0.04317, 0.04358, 0.02421, 0.04792, 0.03182, 0.03674, 0.03361, 0.04111, 0.02487, 0.02488, 0.03823, 0.03821, 0.03974, 0.03678, 0.0398, 0.02984, 0.03478, 0.04022 ], "comparison": { "original": "Gross that", "retranscribed": "Gross.", "reference_tokens": [ "gross", "that" ], "hypothesis_tokens": [ "gross" ], "counts": { "substitutions": 0, "deletions": 1, "insertions": 0, "hits": 1, "reference_words": 2, "hypothesis_words": 1, "edits": 1 }, "wer": 0.5, "wer_percent": 50.0, "alignment": [ { "op": "equal", "reference": "gross", "hypothesis": "gross", "reference_index": 0, "hypothesis_index": 0 }, { "op": "delete", "reference": "that", "hypothesis": null, "reference_index": 1, "hypothesis_index": null } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.60211, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Disgusted", "emotion_confidence": 0.5630421042442322, "duration_seconds": 1.092000000000013, "mos": 3.008, "audio_variant": "cleaned", "original_transcript_raw": "That smell", "original_transcript": "That smell", "retranscribed_transcript": "That smell.", "backend": "qwen", "emotion_analyzed_seconds": 1.092, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-023", "energy": { "value": 0.57421875, "bucket": "medium" }, "audio_url": "audio/utterance-023.wav", "spectrogram_url": "spectrograms/utterance-023.png", "waveform": [ 0.08426, 0.09739, 0.07535, 0.08006, 0.08413, 0.07265, 0.06274, 0.03429, 0.04507, 0.04477, 0.03337, 0.04053, 0.02778, 0.03102, 0.03252, 0.0255, 0.02021, 0.0138, 0.01364, 0.00928, 0.00668, 0.00488, 0.00616, 0.00723, 0.00514, 0.01765, 0.02718, 0.03546, 0.03766, 0.0609, 0.07706, 0.06891, 0.10439, 0.12794, 0.1071, 0.10505, 0.12874, 0.08923, 0.1146, 0.08905, 0.10015, 0.09878, 0.07855, 0.05095, 0.01481, 0.00405, 0.00337, 0.00147, 0.00058, 0.00048, 0.00107, 0.00674, 0.00534, 0.01058, 0.00914, 0.01897, 0.02078, 0.02511, 0.03411, 0.03395, 0.03264, 0.05054, 0.0371, 0.03544, 0.04153, 0.0549, 0.06067, 0.04356, 0.05276, 0.04724, 0.04233, 0.03501, 0.02469, 0.02798, 0.01428, 0.00502, 0.00419, 0.01268, 0.01751, 0.02926, 0.03423, 0.03892, 0.03914, 0.03935, 0.03945, 0.04456, 0.04819, 0.04776, 0.08311, 0.08093, 0.07437, 0.07715, 0.08953, 0.07678, 0.10166, 0.09303, 0.11124, 0.13563, 0.11267, 0.10104, 0.10637, 0.10361, 0.16242, 0.15028, 0.16724, 0.13264, 0.17719, 0.14551, 0.15927, 0.18871, 0.16709, 0.19742, 0.1421, 0.19202, 0.14805, 0.23141, 0.23318, 0.24935, 0.30821, 0.23734, 0.23943, 0.31062, 0.27156, 0.26458, 0.25562, 0.25261, 0.21866, 0.20758, 0.19076, 0.15007, 0.17718, 0.16186, 0.15574, 0.13432, 0.09927, 0.04295, 0.09717, 0.07906, 0.04993, 0.03013, 0.02848, 0.02909, 0.02269, 0.02207, 0.01582, 0.00731, 0.00623, 0.00325, 0.00071, 0.00063, 0.0003, 0.00013, 0.00019, 9e-05, 0.00011, 0.0001, 8e-05, 7e-05, 7e-05, 6e-05, 6e-05, 6e-05, 6e-05, 5e-05, 5e-05, 5e-05, 4e-05, 4e-05, 4e-05, 4e-05, 3e-05, 0.00013, 0.00067, 0.00217, 0.00182, 0.00406, 0.00422, 0.00522, 0.00799, 0.01145 ], "comparison": { "original": "That smell", "retranscribed": "That smell.", "reference_tokens": [ "that", "smell" ], "hypothesis_tokens": [ "that", "smell" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 2, "hypothesis_words": 2, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "smell", "hypothesis": "smell", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.31062, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Disgusted", "emotion_confidence": 0.6484485864639282, "duration_seconds": 1.0749999999999886, "mos": 3.2976, "audio_variant": "cleaned", "original_transcript_raw": "अगली", "original_transcript": "अगली", "retranscribed_transcript": "Ugly.", "backend": "qwen", "emotion_analyzed_seconds": 1.075, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-024", "energy": { "value": 0.54296875, "bucket": "medium" }, "audio_url": "audio/utterance-024.wav", "spectrogram_url": "spectrograms/utterance-024.png", "waveform": [ 0.03411, 0.02259, 0.01333, 0.01889, 0.08938, 0.21503, 0.24688, 0.28071, 0.33543, 0.29689, 0.29364, 0.29224, 0.29397, 0.2918, 0.28048, 0.36193, 0.35154, 0.35103, 0.25769, 0.30401, 0.27715, 0.19624, 0.21757, 0.23708, 0.23027, 0.19231, 0.17024, 0.22655, 0.12499, 0.08837, 0.08708, 0.09248, 0.10073, 0.10266, 0.09547, 0.0849, 0.07781, 0.06224, 0.06414, 0.07007, 0.09765, 0.0816, 0.11047, 0.14642, 0.17322, 0.20026, 0.18455, 0.17305, 0.19849, 0.18527, 0.1755, 0.18752, 0.16703, 0.19268, 0.18438, 0.16912, 0.18314, 0.17258, 0.16736, 0.16089, 0.16367, 0.20134, 0.25294, 0.22138, 0.23203, 0.2666, 0.26152, 0.27129, 0.24173, 0.23837, 0.24955, 0.19677, 0.26995, 0.24257, 0.23633, 0.27938, 0.19421, 0.29386, 0.29707, 0.25615, 0.28238, 0.2883, 0.18426, 0.28806, 0.29956, 0.29955, 0.2838, 0.17021, 0.26475, 0.26578, 0.25967, 0.29656, 0.25964, 0.30094, 0.27386, 0.23624, 0.11621, 0.13621, 0.1029, 0.07567, 0.07297, 0.05137, 0.04054, 0.04628, 0.03424, 0.02852, 0.02261, 0.01317, 0.01165, 0.00648, 0.004, 0.00206, 0.00095, 0.00024, 0.00026, 0.00017, 0.00018, 0.00016, 0.00017, 0.00015, 0.00015, 0.00015, 0.00014, 0.00012, 0.00012, 0.0001, 0.0001, 8e-05, 8e-05, 7e-05, 7e-05, 7e-05, 6e-05, 6e-05, 5e-05, 4e-05, 4e-05, 5e-05, 3e-05, 4e-05, 4e-05, 6e-05, 8e-05, 8e-05, 7e-05, 7e-05, 8e-05, 7e-05, 6e-05, 6e-05, 5e-05, 5e-05, 5e-05, 4e-05, 4e-05, 4e-05, 4e-05, 3e-05, 4e-05, 3e-05, 4e-05, 3e-05, 4e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 0.00066, 0.00225, 0.00437, 0.00459, 0.00873, 0.01446, 0.02245, 0.01876, 0.01664 ], "comparison": { "original": "अगली", "retranscribed": "Ugly.", "reference_tokens": [ "अगली" ], "hypothesis_tokens": [ "ugly" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 0, "reference_words": 1, "hypothesis_words": 1, "edits": 1 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "substitute", "reference": "अगली", "hypothesis": "ugly", "reference_index": 0, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.36193, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Disgusted", "emotion_confidence": 0.694624662399292, "duration_seconds": 3.770999999999958, "mos": 3.4756, "audio_variant": "cleaned", "original_transcript_raw": "Very disturbing facts have come to light here. ", "original_transcript": "Very disturbing facts have come to light here.", "retranscribed_transcript": "Very disturbing facts have come to light here.", "backend": "qwen", "emotion_analyzed_seconds": 3.771, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-025", "energy": { "value": 0.58984375, "bucket": "high" }, "audio_url": "audio/utterance-025.wav", "spectrogram_url": "spectrograms/utterance-025.png", "waveform": [ 0.21549, 0.11969, 0.04153, 0.10164, 0.36614, 0.37613, 0.3614, 0.38593, 0.5024, 0.50628, 0.45571, 0.39114, 0.3276, 0.31862, 0.28671, 0.25511, 0.23032, 0.18199, 0.1512, 0.13283, 0.10369, 0.0836, 0.07728, 0.05381, 0.03171, 0.01934, 0.00908, 0.00481, 0.00171, 0.09494, 0.13972, 0.20516, 0.22748, 0.23153, 0.12857, 0.08569, 0.10892, 0.1353, 0.1455, 0.17926, 0.13609, 0.10937, 0.10359, 0.00585, 0.00095, 0.15577, 0.28952, 0.39485, 0.34844, 0.36095, 0.31271, 0.33557, 0.34223, 0.32738, 0.22444, 0.13934, 0.11023, 0.18902, 0.28116, 0.26589, 0.22148, 0.16529, 0.16428, 0.15124, 0.09192, 0.04075, 0.03586, 0.03032, 0.0367, 0.02475, 0.37399, 0.49591, 0.53943, 0.47748, 0.40307, 0.40711, 0.43812, 0.40753, 0.33509, 0.2697, 0.1636, 0.10977, 0.03508, 0.00822, 0.00618, 0.03404, 0.04262, 0.06637, 0.05388, 0.03799, 0.03224, 0.08172, 0.15705, 0.22784, 0.20369, 0.23441, 0.1818, 0.24774, 0.23162, 0.2322, 0.23246, 0.31295, 0.29418, 0.24639, 0.16394, 0.13296, 0.09255, 0.05142, 0.03075, 0.02194, 0.01826, 0.01779, 0.01356, 0.01027, 0.00685, 0.00517, 0.00312, 0.00201, 0.00153, 0.00128, 0.0013, 0.00124, 0.00137, 0.00116, 0.00097, 0.00114, 0.13208, 0.07529, 0.06945, 0.29111, 0.37171, 0.34601, 0.34978, 0.40077, 0.24679, 0.23485, 0.22266, 0.17769, 0.08913, 0.09377, 0.05983, 0.05356, 0.12506, 0.23304, 0.24515, 0.2103, 0.25288, 0.33085, 0.39195, 0.41479, 0.37197, 0.34757, 0.32068, 0.31178, 0.24338, 0.24893, 0.2033, 0.08677, 0.04467, 0.04699, 0.06948, 0.10534, 0.15709, 0.17176, 0.19725, 0.19425, 0.25422, 0.16578, 0.19784, 0.19595, 0.13758, 0.09446, 0.06291, 0.07048, 0.04283, 0.03213, 0.01523, 0.01004, 0.04062, 0.1018 ], "comparison": { "original": "Very disturbing facts have come to light here.", "retranscribed": "Very disturbing facts have come to light here.", "reference_tokens": [ "very", "disturbing", "facts", "have", "come", "to", "light", "here" ], "hypothesis_tokens": [ "very", "disturbing", "facts", "have", "come", "to", "light", "here" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 8, "reference_words": 8, "hypothesis_words": 8, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "very", "hypothesis": "very", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "disturbing", "hypothesis": "disturbing", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "facts", "hypothesis": "facts", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "have", "hypothesis": "have", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "come", "hypothesis": "come", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "light", "hypothesis": "light", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "here", "hypothesis": "here", "reference_index": 7, "hypothesis_index": 7 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.53943, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Disgusted", "emotion_confidence": 0.47772976756095886, "duration_seconds": 1.5699999999999932, "mos": 2.8771, "audio_variant": "cleaned", "original_transcript_raw": "What's that awful smell? ", "original_transcript": "What's that awful smell?", "retranscribed_transcript": "What's that awful smell?", "backend": "qwen", "emotion_analyzed_seconds": 1.57, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-026", "energy": { "value": 0.68359375, "bucket": "high" }, "audio_url": "audio/utterance-026.wav", "spectrogram_url": "spectrograms/utterance-026.png", "waveform": [ 0.04767, 0.07263, 0.06431, 0.06459, 0.09889, 0.14313, 0.15669, 0.13003, 0.10815, 0.11015, 0.10746, 0.10683, 0.09382, 0.07372, 0.02996, 0.02023, 0.02359, 0.02773, 0.03135, 0.02338, 0.0215, 0.0198, 0.00919, 0.00364, 0.00218, 0.00318, 0.00777, 0.02538, 0.12884, 0.19641, 0.21696, 0.18958, 0.17917, 0.20334, 0.18886, 0.18421, 0.15525, 0.14401, 0.14816, 0.14606, 0.20169, 0.18799, 0.15026, 0.11874, 0.04285, 0.01153, 0.00439, 0.00537, 0.00154, 0.00131, 0.00108, 0.00071, 0.0009, 0.00076, 0.00042, 0.00262, 0.19385, 0.49306, 0.35045, 0.38264, 0.37867, 0.35248, 0.37338, 0.33606, 0.2959, 0.30097, 0.26784, 0.22274, 0.20573, 0.18406, 0.14566, 0.13004, 0.12212, 0.10673, 0.10114, 0.07271, 0.03746, 0.0226, 0.01035, 0.00424, 0.00152, 0.00181, 0.00217, 0.00254, 0.00403, 0.02916, 0.05369, 0.08587, 0.11041, 0.12669, 0.13333, 0.14259, 0.14801, 0.15563, 0.15965, 0.14619, 0.12856, 0.09406, 0.09317, 0.05186, 0.05065, 0.03481, 0.02822, 0.02127, 0.02403, 0.02629, 0.02964, 0.02771, 0.0355, 0.02691, 0.02887, 0.02705, 0.02767, 0.02206, 0.02607, 0.02482, 0.01696, 0.02909, 0.06408, 0.10379, 0.11902, 0.13195, 0.13711, 0.14017, 0.14236, 0.15334, 0.16209, 0.16593, 0.16605, 0.18932, 0.19896, 0.18965, 0.19155, 0.18935, 0.19068, 0.2324, 0.22757, 0.23742, 0.2311, 0.21228, 0.20714, 0.22124, 0.221, 0.2079, 0.21921, 0.2014, 0.20424, 0.21422, 0.22431, 0.25743, 0.25757, 0.23686, 0.20658, 0.21065, 0.21519, 0.19246, 0.1568, 0.11971, 0.1081, 0.11283, 0.11262, 0.11518, 0.11456, 0.08994, 0.07783, 0.06061, 0.04562, 0.03376, 0.02662, 0.01583, 0.00772, 0.00612, 0.00539, 0.00301, 0.00355, 0.00683, 0.01025, 0.01831, 0.029, 0.02075 ], "comparison": { "original": "What's that awful smell?", "retranscribed": "What's that awful smell?", "reference_tokens": [ "whats", "that", "awful", "smell" ], "hypothesis_tokens": [ "whats", "that", "awful", "smell" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 4, "reference_words": 4, "hypothesis_words": 4, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "whats", "hypothesis": "whats", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "awful", "hypothesis": "awful", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "smell", "hypothesis": "smell", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.49306, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Disgusted", "emotion_confidence": 0.3462607264518738, "duration_seconds": 8.15700000000001, "mos": 3.5092, "audio_variant": "cleaned", "original_transcript_raw": "I cannot believe what my skin looks like, but my wow faster are my eyes. I cannot get over. ", "original_transcript": "I cannot believe what my skin looks like, but my wow faster are my eyes. I cannot get over.", "retranscribed_transcript": "I cannot believe what my skin looks like. But my wow factor are my eyes. I cannot get over.", "backend": "qwen", "emotion_analyzed_seconds": 8.157, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-027", "energy": { "value": 0.640625, "bucket": "high" }, "audio_url": "audio/utterance-027.wav", "spectrogram_url": "spectrograms/utterance-027.png", "waveform": [ 0.02175, 0.12723, 0.13203, 0.12687, 0.22112, 0.16857, 0.1625, 0.16154, 0.15878, 0.12785, 0.01312, 0.00326, 0.00309, 0.00154, 0.00164, 0.10377, 0.14975, 0.23865, 0.25606, 0.22559, 0.21208, 0.23302, 0.11644, 0.01207, 0.07577, 0.04673, 0.23314, 0.22351, 0.18389, 0.13907, 0.11918, 0.12738, 0.15624, 0.08951, 0.09085, 0.06105, 0.05678, 0.05582, 0.04282, 0.01879, 0.01862, 0.00227, 0.11922, 0.24094, 0.36528, 0.16857, 0.0916, 0.11367, 0.0925, 0.08421, 0.0409, 0.02309, 0.16792, 0.17047, 0.1203, 0.11446, 0.10793, 0.09049, 0.1089, 0.05909, 0.01322, 0.11811, 0.13057, 0.09025, 0.0833, 0.05822, 0.00195, 0.15574, 0.26275, 0.23678, 0.25557, 0.13269, 0.00241, 0.02208, 0.13512, 0.19658, 0.18438, 0.15622, 0.11987, 0.13393, 0.18796, 0.24744, 0.2614, 0.26249, 0.16048, 0.0363, 0.03916, 0.24861, 0.27862, 0.27526, 0.17327, 0.03489, 0.00952, 0.15005, 0.24759, 0.20897, 0.20417, 0.18827, 0.14401, 0.02907, 0.03869, 0.00183, 0.0014, 0.2386, 0.18485, 0.18369, 0.16908, 0.15474, 0.15328, 0.15072, 0.15061, 0.14089, 0.05585, 0.00905, 0.00501, 0.11183, 0.14268, 0.1643, 0.18269, 0.20816, 0.13106, 0.00637, 0.49575, 0.15817, 0.1447, 0.18839, 0.12597, 0.11447, 0.13434, 0.08613, 0.08157, 0.04008, 0.03903, 0.04097, 0.11227, 0.00158, 0.24581, 0.28571, 0.2296, 0.00626, 0.10965, 0.13618, 0.07289, 0.1684, 0.15739, 0.13481, 0.13694, 0.21949, 0.22204, 0.17478, 0.18075, 0.17772, 0.29306, 0.01449, 0.0387, 0.0515, 0.02935, 0.0283, 0.01454, 0.17439, 0.25804, 0.21677, 0.03518, 0.0078, 0.17659, 0.21809, 0.19706, 0.16663, 0.06554, 0.22074, 0.22926, 0.16011, 0.14403, 0.0728, 0.02758, 0.0124, 0.00239, 0.00146, 0.00136, 0.02157 ], "comparison": { "original": "I cannot believe what my skin looks like, but my wow faster are my eyes. I cannot get over.", "retranscribed": "I cannot believe what my skin looks like. But my wow factor are my eyes. I cannot get over.", "reference_tokens": [ "i", "cannot", "believe", "what", "my", "skin", "looks", "like", "but", "my", "wow", "faster", "are", "my", "eyes", "i", "cannot", "get", "over" ], "hypothesis_tokens": [ "i", "cannot", "believe", "what", "my", "skin", "looks", "like", "but", "my", "wow", "factor", "are", "my", "eyes", "i", "cannot", "get", "over" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 18, "reference_words": 19, "hypothesis_words": 19, "edits": 1 }, "wer": 0.05263157894736842, "wer_percent": 5.263157894736842, "alignment": [ { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "cannot", "hypothesis": "cannot", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "believe", "hypothesis": "believe", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "what", "hypothesis": "what", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "skin", "hypothesis": "skin", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "looks", "hypothesis": "looks", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "like", "hypothesis": "like", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "but", "hypothesis": "but", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "wow", "hypothesis": "wow", "reference_index": 10, "hypothesis_index": 10 }, { "op": "substitute", "reference": "faster", "hypothesis": "factor", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "are", "hypothesis": "are", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "eyes", "hypothesis": "eyes", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "cannot", "hypothesis": "cannot", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "get", "hypothesis": "get", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "over", "hypothesis": "over", "reference_index": 18, "hypothesis_index": 18 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.49575, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Fearful", "emotion_confidence": 0.40689775347709656, "duration_seconds": 0.6999999999999886, "mos": 3.5649, "audio_variant": "original", "original_transcript_raw": "Little nervous", "original_transcript": "Little nervous", "retranscribed_transcript": "A little nervous.", "backend": "qwen", "emotion_analyzed_seconds": 0.7, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-028", "energy": { "value": 0.470703125, "bucket": "low" }, "audio_url": "audio/utterance-028.wav", "spectrogram_url": "spectrograms/utterance-028.png", "waveform": [ 0.01179, 0.06192, 0.03862, 0.07276, 0.08488, 0.01299, 0.04834, 0.05184, 0.0194, 0.04788, 0.03107, 0.01793, 0.03174, 0.07779, 0.04548, 0.04328, 0.09358, 0.05925, 0.14593, 0.0653, 0.02061, 0.0405, 0.03838, 0.13181, 0.0676, 0.02664, 0.11404, 0.03318, 0.0182, 0.04902, 0.13636, 0.16308, 0.03095, 0.17096, 0.12039, 0.0496, 0.07998, 0.19698, 0.11576, 0.04531, 0.06226, 0.03094, 0.02451, 0.09037, 0.02679, 0.02747, 0.02015, 0.04772, 0.01619, 0.0551, 0.04476, 0.02096, 0.03763, 0.03501, 0.02522, 0.05087, 0.03614, 0.0201, 0.05008, 0.03591, 0.02786, 0.08475, 0.05687, 0.02049, 0.1315, 0.04413, 0.04597, 0.15716, 0.04609, 0.00987, 0.06994, 0.02554, 0.106, 0.08792, 0.02121, 0.07114, 0.05713, 0.01187, 0.10977, 0.06352, 0.01431, 0.12734, 0.0567, 0.01241, 0.12522, 0.04781, 0.01934, 0.14091, 0.02364, 0.14833, 0.08385, 0.02024, 0.14497, 0.04693, 0.02137, 0.08224, 0.01889, 0.00864, 0.08653, 0.01341, 0.01536, 0.02053, 0.0814, 0.01794, 0.01496, 0.01075, 0.01379, 0.00892, 0.03869, 0.00996, 0.00854, 0.00557, 0.05592, 0.01694, 0.00464, 0.0081, 0.00793, 0.00874, 0.02152, 0.17852, 0.08843, 0.02385, 0.01184, 0.01061, 0.04355, 0.27528, 0.22988, 0.1084, 0.0649, 0.02697, 0.02783, 0.00829, 0.007, 0.00626, 0.01152, 0.01076, 0.00905, 0.0334, 0.19768, 0.09749, 0.04198, 0.00798, 0.01604, 0.00942, 0.0128, 0.01422, 0.04158, 0.02367, 0.02158, 0.02675, 0.02893, 0.04781, 0.02109, 0.02357, 0.02798, 0.02412, 0.01934, 0.01603, 0.02402, 0.01525, 0.02634, 0.01658, 0.02008, 0.01604, 0.01453, 0.01395, 0.01796, 0.0158, 0.01434, 0.01151, 0.01224, 0.00805, 0.01051, 0.01226, 0.00823, 0.01019, 0.00753, 0.00775, 0.00413, 0.0042 ], "comparison": { "original": "Little nervous", "retranscribed": "A little nervous.", "reference_tokens": [ "little", "nervous" ], "hypothesis_tokens": [ "a", "little", "nervous" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 2, "reference_words": 2, "hypothesis_words": 3, "edits": 1 }, "wer": 0.5, "wer_percent": 50.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "a", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "little", "hypothesis": "little", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "nervous", "hypothesis": "nervous", "reference_index": 1, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.27528, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Fearful", "emotion_confidence": 0.6463403105735779, "duration_seconds": 1.3310000000000173, "mos": 3.1523, "audio_variant": "cleaned", "original_transcript_raw": "I am still afraid for you. ", "original_transcript": "I am still afraid for you.", "retranscribed_transcript": "I am still afraid for you.", "backend": "qwen", "emotion_analyzed_seconds": 1.331, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-029", "energy": { "value": 0.42578125, "bucket": "low" }, "audio_url": "audio/utterance-029.wav", "spectrogram_url": "spectrograms/utterance-029.png", "waveform": [ 0.01363, 0.01852, 0.1214, 0.11091, 0.17287, 0.17856, 0.2754, 0.26286, 0.30075, 0.3534, 0.35013, 0.3323, 0.33073, 0.31844, 0.32811, 0.31625, 0.29745, 0.23004, 0.2038, 0.21262, 0.23698, 0.24661, 0.25478, 0.23996, 0.23674, 0.24577, 0.20735, 0.135, 0.11491, 0.08076, 0.04313, 0.06001, 0.06694, 0.07825, 0.05544, 0.04351, 0.05265, 0.0749, 0.0129, 0.00783, 0.00255, 0.00213, 0.00391, 0.08594, 0.15541, 0.08865, 0.07341, 0.28246, 0.58716, 0.61273, 0.33354, 0.30681, 0.23577, 0.20095, 0.2013, 0.21007, 0.19512, 0.18843, 0.179, 0.16982, 0.18179, 0.21481, 0.18372, 0.17215, 0.13673, 0.07575, 0.0448, 0.04415, 0.04835, 0.04622, 0.04689, 0.03378, 0.0426, 0.03872, 0.03006, 0.03288, 0.03058, 0.02476, 0.03027, 0.03856, 0.03558, 0.02801, 0.02744, 0.04037, 0.21695, 0.18628, 0.31237, 0.35562, 0.30052, 0.28658, 0.28124, 0.29669, 0.27901, 0.27489, 0.22966, 0.18625, 0.17154, 0.16816, 0.19011, 0.17747, 0.17435, 0.03495, 0.01295, 0.00606, 0.0032, 0.00347, 0.16599, 0.09807, 0.08884, 0.05555, 0.03786, 0.0159, 0.01127, 0.00239, 0.00224, 0.00184, 0.00119, 0.00172, 0.09967, 0.07397, 0.05957, 0.05935, 0.04652, 0.0351, 0.05038, 0.0534, 0.04363, 0.04312, 0.03097, 0.02188, 0.02144, 0.03784, 0.05827, 0.11607, 0.13485, 0.13772, 0.12038, 0.13283, 0.11798, 0.12997, 0.0986, 0.10927, 0.10562, 0.11085, 0.12362, 0.10887, 0.11836, 0.10962, 0.13423, 0.10998, 0.10741, 0.121, 0.10027, 0.10517, 0.07238, 0.06441, 0.06507, 0.05968, 0.05789, 0.02587, 0.02757, 0.03956, 0.0326, 0.02659, 0.02156, 0.022, 0.02045, 0.01513, 0.01014, 0.00444, 0.00399, 0.00416, 0.00331, 0.00347, 0.00578, 0.01039, 0.01567, 0.01614, 0.02316, 0.02512 ], "comparison": { "original": "I am still afraid for you.", "retranscribed": "I am still afraid for you.", "reference_tokens": [ "i", "am", "still", "afraid", "for", "you" ], "hypothesis_tokens": [ "i", "am", "still", "afraid", "for", "you" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 6, "reference_words": 6, "hypothesis_words": 6, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "am", "hypothesis": "am", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "still", "hypothesis": "still", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "afraid", "hypothesis": "afraid", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "for", "hypothesis": "for", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.61273, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Fearful", "emotion_confidence": 0.5411466360092163, "duration_seconds": 1.6210000000000093, "mos": 3.1139, "audio_variant": "original", "original_transcript_raw": "Dad, please don't lie to me. ", "original_transcript": "Dad, please don't lie to me.", "retranscribed_transcript": "Dad, please don't lie to me.", "backend": "qwen", "emotion_analyzed_seconds": 1.621, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-030", "energy": { "value": 0.5078125, "bucket": "low" }, "audio_url": "audio/utterance-030.wav", "spectrogram_url": "spectrograms/utterance-030.png", "waveform": [ 0.02077, 0.02063, 0.01777, 0.0188, 0.02127, 0.05154, 0.052, 0.058, 0.06962, 0.07546, 0.05604, 0.06024, 0.05746, 0.06168, 0.05785, 0.06173, 0.06892, 0.06177, 0.06665, 0.06016, 0.05546, 0.06144, 0.06448, 0.06509, 0.05919, 0.06427, 0.06599, 0.06492, 0.06452, 0.07141, 0.07434, 0.07698, 0.06442, 0.0191, 0.02456, 0.01814, 0.01766, 0.01663, 0.00952, 0.02325, 0.01902, 0.01099, 0.00741, 0.00809, 0.00547, 0.00725, 0.00658, 0.00839, 0.00627, 0.00884, 0.00919, 0.00757, 0.00721, 0.00611, 0.00849, 0.00825, 0.0072, 0.00866, 0.00917, 0.00863, 0.00636, 0.0073, 0.00778, 0.00757, 0.00823, 0.00767, 0.01442, 0.01401, 0.05763, 0.05298, 0.0599, 0.05983, 0.05611, 0.05279, 0.04488, 0.03664, 0.0372, 0.03292, 0.03379, 0.02833, 0.0288, 0.02803, 0.02511, 0.02816, 0.02058, 0.01495, 0.01478, 0.0176, 0.01106, 0.01126, 0.00578, 0.01149, 0.0186, 0.05459, 0.05224, 0.05778, 0.05461, 0.0548, 0.04606, 0.05061, 0.0492, 0.0432, 0.04415, 0.03534, 0.03147, 0.02753, 0.03521, 0.02717, 0.02695, 0.0278, 0.03005, 0.02769, 0.02749, 0.03176, 0.0231, 0.03893, 0.06072, 0.05925, 0.05508, 0.05301, 0.05096, 0.05275, 0.06178, 0.05238, 0.03611, 0.03509, 0.03364, 0.03038, 0.02354, 0.00792, 0.00861, 0.00546, 0.00686, 0.00435, 0.00558, 0.00371, 0.01227, 0.00818, 0.00888, 0.01354, 0.01601, 0.01614, 0.01741, 0.01317, 0.01391, 0.01174, 0.01048, 0.00969, 0.00686, 0.0109, 0.03729, 0.03236, 0.03088, 0.02559, 0.03035, 0.02819, 0.02952, 0.02851, 0.02602, 0.02933, 0.02467, 0.0322, 0.03157, 0.02887, 0.02507, 0.02434, 0.02817, 0.0312, 0.02848, 0.02622, 0.02472, 0.02579, 0.02261, 0.02594, 0.02488, 0.01785, 0.0115, 0.00805, 0.0068, 0.00651 ], "comparison": { "original": "Dad, please don't lie to me.", "retranscribed": "Dad, please don't lie to me.", "reference_tokens": [ "dad", "please", "dont", "lie", "to", "me" ], "hypothesis_tokens": [ "dad", "please", "dont", "lie", "to", "me" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 6, "reference_words": 6, "hypothesis_words": 6, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "dad", "hypothesis": "dad", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "please", "hypothesis": "please", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "dont", "hypothesis": "dont", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "lie", "hypothesis": "lie", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.07698, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Fearful", "emotion_confidence": 0.6147894859313965, "duration_seconds": 0.9730000000000132, "mos": 3.4065, "audio_variant": "cleaned", "original_transcript_raw": "I was afraid", "original_transcript": "I was afraid", "retranscribed_transcript": "I was afraid.", "backend": "qwen", "emotion_analyzed_seconds": 0.973, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-031", "energy": { "value": 0.578125, "bucket": "medium" }, "audio_url": "audio/utterance-031.wav", "spectrogram_url": "spectrograms/utterance-031.png", "waveform": [ 0.00999, 0.00732, 0.00962, 0.02689, 0.06593, 0.0544, 0.16177, 0.22421, 0.14456, 0.30709, 0.32887, 0.21585, 0.36622, 0.38014, 0.33683, 0.33451, 0.3442, 0.37851, 0.36811, 0.38953, 0.4267, 0.3397, 0.44242, 0.41884, 0.44483, 0.39709, 0.44148, 0.3639, 0.41612, 0.35882, 0.35209, 0.26503, 0.20041, 0.08906, 0.10653, 0.06977, 0.06766, 0.05467, 0.08208, 0.08431, 0.09365, 0.08137, 0.12753, 0.09097, 0.08193, 0.0852, 0.12054, 0.19019, 0.24896, 0.27851, 0.35698, 0.41024, 0.39077, 0.52171, 0.5776, 0.57537, 0.35203, 0.50607, 0.56796, 0.54593, 0.61305, 0.53444, 0.39052, 0.43445, 0.31025, 0.29604, 0.18401, 0.07823, 0.10802, 0.05097, 0.05133, 0.03564, 0.0374, 0.02939, 0.03784, 0.02976, 0.03801, 0.04901, 0.03157, 0.03583, 0.04758, 0.0661, 0.05656, 0.04845, 0.0568, 0.07772, 0.06824, 0.06832, 0.06978, 0.07393, 0.06679, 0.08193, 0.07628, 0.05798, 0.06708, 0.06912, 0.03512, 0.1124, 0.12644, 0.10722, 0.15717, 0.22127, 0.36951, 0.39715, 0.31324, 0.35121, 0.3321, 0.33923, 0.23843, 0.19974, 0.2483, 0.34388, 0.32802, 0.35735, 0.47074, 0.53851, 0.47098, 0.40312, 0.42512, 0.42936, 0.44542, 0.34175, 0.24953, 0.25499, 0.28499, 0.27376, 0.23342, 0.28499, 0.22547, 0.19176, 0.19451, 0.20783, 0.20699, 0.13872, 0.12385, 0.05396, 0.05543, 0.05678, 0.05616, 0.04779, 0.03908, 0.0263, 0.01533, 0.01035, 0.01009, 0.00561, 0.00575, 0.00369, 0.00222, 0.00102, 0.00078, 0.00075, 0.0005, 0.00087, 0.02476, 0.04068, 0.04869, 0.04851, 0.04413, 0.04078, 0.03784, 0.03974, 0.02121, 0.01697, 0.01468, 0.01229, 0.00883, 0.00532, 0.00313, 0.00338, 0.00261, 0.00207, 0.00188, 0.00304, 0.00391, 0.00671, 0.00569, 0.00904, 0.00771, 0.00661 ], "comparison": { "original": "I was afraid", "retranscribed": "I was afraid.", "reference_tokens": [ "i", "was", "afraid" ], "hypothesis_tokens": [ "i", "was", "afraid" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 3, "reference_words": 3, "hypothesis_words": 3, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "was", "hypothesis": "was", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "afraid", "hypothesis": "afraid", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.61305, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Fearful", "emotion_confidence": 0.29919812083244324, "duration_seconds": 0.8540000000000001, "mos": 2.9612, "audio_variant": "cleaned", "original_transcript_raw": "आई एम अफ्रेड। ", "original_transcript": "आई एम अफ्रेड।", "retranscribed_transcript": "I'm afraid.", "backend": "qwen", "emotion_analyzed_seconds": 0.854, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-032", "energy": { "value": 0.56640625, "bucket": "medium" }, "audio_url": "audio/utterance-032.wav", "spectrogram_url": "spectrograms/utterance-032.png", "waveform": [ 0.02003, 0.04446, 0.02585, 0.03899, 0.02331, 0.03559, 0.05722, 0.04611, 0.02808, 0.06064, 0.05151, 0.21225, 0.10313, 0.17442, 0.10622, 0.09495, 0.0884, 0.10433, 0.15145, 0.12527, 0.16068, 0.18931, 0.19319, 0.19801, 0.22386, 0.22624, 0.21402, 0.24558, 0.32273, 0.40664, 0.37877, 0.52809, 0.51218, 0.38366, 0.52715, 0.54467, 0.52137, 0.35333, 0.49231, 0.31813, 0.2797, 0.24047, 0.09231, 0.07203, 0.05889, 0.06265, 0.02565, 0.01682, 0.01626, 0.01322, 0.00974, 0.00984, 0.01071, 0.00805, 0.0161, 0.01954, 0.01612, 0.01591, 0.02227, 0.02156, 0.03177, 0.02778, 0.03578, 0.03668, 0.02421, 0.0197, 0.01463, 0.02314, 0.04042, 0.03929, 0.08742, 0.04519, 0.07462, 0.13703, 0.17139, 0.17962, 0.257, 0.23102, 0.28116, 0.21867, 0.23797, 0.32455, 0.35109, 0.30271, 0.40023, 0.44698, 0.48458, 0.47991, 0.47659, 0.38528, 0.43298, 0.4333, 0.47458, 0.48321, 0.4528, 0.51437, 0.42858, 0.43293, 0.46494, 0.49758, 0.46776, 0.45497, 0.43736, 0.43392, 0.38489, 0.41987, 0.31325, 0.2262, 0.15158, 0.10505, 0.10505, 0.10023, 0.10003, 0.08683, 0.09145, 0.07795, 0.07777, 0.06809, 0.06609, 0.07127, 0.05941, 0.04825, 0.05695, 0.05049, 0.04374, 0.04318, 0.03876, 0.03855, 0.03439, 0.02694, 0.02773, 0.02704, 0.02365, 0.02659, 0.0207, 0.02556, 0.01544, 0.02331, 0.01912, 0.01949, 0.01705, 0.01572, 0.01522, 0.01236, 0.00977, 0.00879, 0.00973, 0.00574, 0.0065, 0.00443, 0.00343, 0.00319, 0.00157, 0.00138, 0.00088, 0.00064, 0.00051, 0.00058, 0.00045, 0.00038, 0.00016, 0.00019, 0.00016, 0.00015, 0.00011, 0.00015, 0.00018, 0.00015, 0.00025, 0.00032, 0.00102, 0.00168, 0.0026, 0.00488, 0.00433, 0.00504, 0.00593, 0.00783, 0.00871, 0.01179 ], "comparison": { "original": "आई एम अफ्रेड।", "retranscribed": "I'm afraid.", "reference_tokens": [ "आई", "एम", "अफ्रेड" ], "hypothesis_tokens": [ "im", "afraid" ], "counts": { "substitutions": 2, "deletions": 1, "insertions": 0, "hits": 0, "reference_words": 3, "hypothesis_words": 2, "edits": 3 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "delete", "reference": "आई", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "substitute", "reference": "एम", "hypothesis": "im", "reference_index": 1, "hypothesis_index": 0 }, { "op": "substitute", "reference": "अफ्रेड", "hypothesis": "afraid", "reference_index": 2, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.54467, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Fearful", "emotion_confidence": 0.21940229833126068, "duration_seconds": 3.7369999999999663, "mos": 3.0048, "audio_variant": "cleaned", "original_transcript_raw": "Ray for this please", "original_transcript": "Ray for this please", "retranscribed_transcript": "You, Rayford, please, please.", "backend": "qwen", "emotion_analyzed_seconds": 3.737, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-033", "energy": { "value": 0.5390625, "bucket": "medium" }, "audio_url": "audio/utterance-033.wav", "spectrogram_url": "spectrograms/utterance-033.png", "waveform": [ 0.16144, 0.07682, 0.11525, 0.21347, 0.27524, 0.27201, 0.26354, 0.23134, 0.16728, 0.13709, 0.11716, 0.10988, 0.09456, 0.0692, 0.04812, 0.0182, 0.01301, 0.00999, 0.00682, 0.00448, 0.0039, 0.00483, 0.00271, 0.00152, 0.00344, 0.00276, 0.00271, 0.0031, 0.00381, 0.0039, 0.00293, 0.00371, 0.00269, 0.0035, 0.00332, 0.00381, 0.00476, 0.00354, 0.00362, 0.00385, 0.0033, 0.00507, 0.00497, 0.00893, 0.01238, 0.01681, 0.01406, 0.08322, 0.12106, 0.08765, 0.06898, 0.05209, 0.04115, 0.02007, 0.00996, 0.01074, 0.01741, 0.00845, 0.00643, 0.00923, 0.01325, 0.00698, 0.00843, 0.00447, 0.00392, 0.0045, 0.00322, 0.00432, 0.00351, 0.00416, 0.00324, 0.00381, 0.004, 0.00657, 0.00738, 0.07766, 0.19824, 0.25091, 0.28848, 0.31594, 0.37575, 0.40036, 0.34008, 0.34936, 0.40296, 0.35503, 0.27795, 0.12478, 0.08243, 0.08603, 0.08176, 0.05855, 0.0524, 0.24555, 0.30682, 0.28785, 0.28142, 0.25758, 0.24308, 0.22237, 0.21112, 0.20851, 0.20421, 0.20995, 0.21353, 0.17346, 0.20106, 0.19195, 0.14758, 0.10791, 0.07763, 0.01596, 0.0113, 0.01271, 0.05079, 0.10146, 0.13926, 0.15241, 0.16943, 0.18327, 0.19103, 0.19549, 0.20757, 0.21739, 0.20671, 0.15516, 0.06884, 0.07177, 0.06199, 0.04937, 0.06057, 0.03536, 0.03798, 0.03036, 0.02406, 0.02294, 0.01351, 0.01672, 0.01169, 0.00907, 0.00593, 0.00663, 0.00351, 0.00274, 0.00312, 0.00186, 0.00255, 0.00296, 0.00279, 0.00398, 0.00391, 0.0036, 0.00409, 0.00657, 0.02186, 0.03442, 0.07012, 0.07437, 0.0764, 0.0698, 0.06275, 0.05768, 0.05503, 0.05986, 0.02569, 0.03019, 0.03037, 0.03814, 0.02558, 0.02565, 0.03337, 0.02768, 0.02212, 0.01784, 0.0137, 0.01017, 0.01142, 0.00884, 0.047, 0.04506 ], "comparison": { "original": "Ray for this please", "retranscribed": "You, Rayford, please, please.", "reference_tokens": [ "ray", "for", "this", "please" ], "hypothesis_tokens": [ "you", "rayford", "please", "please" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 0, "hits": 1, "reference_words": 4, "hypothesis_words": 4, "edits": 3 }, "wer": 0.75, "wer_percent": 75.0, "alignment": [ { "op": "substitute", "reference": "ray", "hypothesis": "you", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "for", "hypothesis": "rayford", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "this", "hypothesis": "please", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "please", "hypothesis": "please", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.40296, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Fearful", "emotion_confidence": 0.3826064467430115, "duration_seconds": 1.2460000000000004, "mos": 3.7446, "audio_variant": "original", "original_transcript_raw": "Ja fair", "original_transcript": "Ja fair", "retranscribed_transcript": "Yeah, scared.", "backend": "qwen", "emotion_analyzed_seconds": 1.246, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-034", "energy": { "value": 0.71484375, "bucket": "high" }, "audio_url": "audio/utterance-034.wav", "spectrogram_url": "spectrograms/utterance-034.png", "waveform": [ 0.00089, 0.00436, 0.01064, 0.10371, 0.29999, 0.44395, 0.42015, 0.37201, 0.28733, 0.29307, 0.3326, 0.31077, 0.26338, 0.27638, 0.4507, 0.38915, 0.41507, 0.33381, 0.36379, 0.25727, 0.33919, 0.42383, 0.27559, 0.39023, 0.2484, 0.28882, 0.28655, 0.22528, 0.36265, 0.4157, 0.23073, 0.19927, 0.32025, 0.33511, 0.26587, 0.2489, 0.33914, 0.20231, 0.17987, 0.18564, 0.186, 0.16654, 0.14094, 0.11592, 0.138, 0.11068, 0.08514, 0.06946, 0.05776, 0.05337, 0.04107, 0.02286, 0.03145, 0.02403, 0.03362, 0.02137, 0.02044, 0.01434, 0.01635, 0.01172, 0.00684, 0.00699, 0.00708, 0.00473, 0.00373, 0.00297, 0.00343, 0.04406, 0.06555, 0.03571, 0.01413, 0.0088, 0.00827, 0.0041, 0.00442, 0.00261, 0.00165, 0.0011, 0.00079, 0.00078, 0.00082, 0.00089, 0.00109, 0.00385, 0.01239, 0.01072, 0.01124, 0.00996, 0.00976, 0.0104, 0.01347, 0.01154, 0.00807, 0.00468, 0.00378, 0.00247, 0.00131, 0.0019, 0.00333, 0.00256, 0.0014, 0.00128, 0.00117, 0.0014, 0.00161, 0.00248, 0.0085, 0.00709, 0.00393, 0.00204, 0.00433, 0.00406, 0.00235, 0.00301, 0.00688, 0.02747, 0.06453, 0.13978, 0.49009, 0.51523, 0.3543, 0.34681, 0.38564, 0.36241, 0.31848, 0.2634, 0.35111, 0.38989, 0.39058, 0.38985, 0.34997, 0.33645, 0.34925, 0.3522, 0.35472, 0.34872, 0.32177, 0.26927, 0.31649, 0.37398, 0.29596, 0.34876, 0.29026, 0.3165, 0.27379, 0.36369, 0.33566, 0.33751, 0.29558, 0.30587, 0.35853, 0.37558, 0.1741, 0.29818, 0.3595, 0.26879, 0.24673, 0.08583, 0.08761, 0.04576, 0.06114, 0.06772, 0.08514, 0.10421, 0.15092, 0.10775, 0.10518, 0.06462, 0.05703, 0.03957, 0.02697, 0.03237, 0.04093, 0.01753, 0.01461, 0.01275, 0.01567, 0.01272, 0.00964, 0.01254 ], "comparison": { "original": "Ja fair", "retranscribed": "Yeah, scared.", "reference_tokens": [ "ja", "fair" ], "hypothesis_tokens": [ "yeah", "scared" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 0, "reference_words": 2, "hypothesis_words": 2, "edits": 2 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "substitute", "reference": "ja", "hypothesis": "yeah", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "fair", "hypothesis": "scared", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.51523, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Fearful", "emotion_confidence": 0.9827415347099304, "duration_seconds": 0.921999999999997, "mos": 3.4622, "audio_variant": "cleaned", "original_transcript_raw": "I'm scared. ", "original_transcript": "I'm scared.", "retranscribed_transcript": "I'm scared.", "backend": "qwen", "emotion_analyzed_seconds": 0.922, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-035", "energy": { "value": 0.78125, "bucket": "high" }, "audio_url": "audio/utterance-035.wav", "spectrogram_url": "spectrograms/utterance-035.png", "waveform": [ 0.115, 0.19439, 0.05826, 0.05081, 0.15326, 0.16556, 0.10681, 0.10281, 0.14102, 0.08853, 0.1052, 0.10397, 0.0914, 0.09706, 0.09673, 0.09398, 0.09242, 0.09746, 0.09687, 0.10125, 0.10527, 0.10409, 0.1083, 0.08049, 0.05217, 0.02516, 0.01595, 0.01024, 0.01041, 0.01395, 0.01705, 0.018, 0.01422, 0.01887, 0.02506, 0.02134, 0.02692, 0.03721, 0.02777, 0.03042, 0.04277, 0.04335, 0.03722, 0.01809, 0.01223, 0.00958, 0.00119, 0.00073, 0.00064, 0.00066, 0.00043, 0.00034, 0.00034, 0.00034, 0.00034, 0.00024, 0.00028, 0.0002, 0.00029, 0.00032, 0.00021, 0.00017, 0.00071, 0.06678, 0.03756, 0.02304, 0.02561, 0.0181, 0.02461, 0.20872, 0.2298, 0.31598, 0.21134, 0.30602, 0.31205, 0.36006, 0.4388, 0.34418, 0.4915, 0.40885, 0.45132, 0.4743, 0.4435, 0.44838, 0.43474, 0.44332, 0.47141, 0.47495, 0.47206, 0.36943, 0.39599, 0.24453, 0.39543, 0.27162, 0.36744, 0.33332, 0.25031, 0.43847, 0.38006, 0.21969, 0.40901, 0.25106, 0.43639, 0.17959, 0.42906, 0.25234, 0.39657, 0.34041, 0.50123, 0.43854, 0.59646, 0.33893, 0.4843, 0.50014, 0.5828, 0.39002, 0.51073, 0.44881, 0.58807, 0.28324, 0.49331, 0.30096, 0.38857, 0.29749, 0.33478, 0.27428, 0.34786, 0.35072, 0.32419, 0.35982, 0.36731, 0.32378, 0.27759, 0.27395, 0.19704, 0.14945, 0.12512, 0.1121, 0.11463, 0.10874, 0.09192, 0.05771, 0.02957, 0.01238, 0.01174, 0.00732, 0.00512, 0.0066, 0.00672, 0.00359, 0.00245, 0.00257, 0.00242, 0.00237, 0.00138, 0.00229, 0.00138, 0.00118, 0.00085, 0.00079, 0.00074, 0.00115, 0.00067, 0.00036, 0.00037, 0.00034, 0.00027, 0.00011, 0.00016, 0.0001, 0.00241, 0.00681, 0.0097, 0.01898, 0.02288, 0.0336, 0.0396, 0.04446, 0.04939, 0.05549 ], "comparison": { "original": "I'm scared.", "retranscribed": "I'm scared.", "reference_tokens": [ "im", "scared" ], "hypothesis_tokens": [ "im", "scared" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 2, "hypothesis_words": 2, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "im", "hypothesis": "im", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "scared", "hypothesis": "scared", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.59646, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Fearful", "emotion_confidence": 0.4221477508544922, "duration_seconds": 2.9350000000000023, "mos": 3.1254, "audio_variant": "cleaned", "original_transcript_raw": "One", "original_transcript": "One", "retranscribed_transcript": "One.", "backend": "qwen", "emotion_analyzed_seconds": 2.935, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-036", "energy": { "value": 0.94140625, "bucket": "high" }, "audio_url": "audio/utterance-036.wav", "spectrogram_url": "spectrograms/utterance-036.png", "waveform": [ 6e-05, 0.00026, 0.0647, 0.15019, 0.22023, 0.25405, 0.29473, 0.34436, 0.51097, 0.61133, 0.67551, 0.69947, 0.64555, 0.60377, 0.53244, 0.41777, 0.24497, 0.22912, 0.21008, 0.19965, 0.18057, 0.1646, 0.15593, 0.0326, 0.00455, 0.00198, 0.00221, 0.00103, 0.00077, 0.00079, 0.0013, 0.00067, 0.00069, 0.00074, 0.00087, 0.00075, 0.00072, 0.00042, 0.00048, 0.0005, 0.00031, 0.00052, 0.00046, 0.00042, 0.00118, 0.01822, 0.05606, 0.05356, 0.06442, 0.07336, 0.10132, 0.18367, 0.1681, 0.1258, 0.17139, 0.24423, 0.60388, 0.63306, 0.47853, 0.42822, 0.47932, 0.53705, 0.54341, 0.34683, 0.54134, 0.48814, 0.53651, 0.44087, 0.56169, 0.57052, 0.61265, 0.68198, 0.61028, 0.54534, 0.53857, 0.43311, 0.6286, 0.61894, 0.5164, 0.55618, 0.57143, 0.5056, 0.43887, 0.50503, 0.4143, 0.46081, 0.48059, 0.49389, 0.39802, 0.45564, 0.50129, 0.5049, 0.59246, 0.59485, 0.63681, 0.43079, 0.57347, 0.6142, 0.62661, 0.52651, 0.46487, 0.38523, 0.34439, 0.40256, 0.37386, 0.40743, 0.332, 0.4811, 0.45046, 0.34616, 0.33735, 0.34446, 0.38373, 0.46845, 0.49542, 0.52252, 0.59208, 0.54049, 0.61609, 0.57273, 0.49428, 0.4903, 0.35292, 0.37452, 0.37819, 0.36898, 0.42782, 0.35305, 0.27772, 0.36384, 0.40338, 0.37797, 0.34174, 0.32855, 0.31811, 0.2924, 0.36481, 0.33399, 0.31645, 0.26538, 0.28919, 0.34669, 0.34543, 0.27725, 0.28618, 0.26809, 0.31882, 0.25717, 0.35368, 0.30782, 0.22645, 0.23485, 0.23842, 0.31128, 0.30487, 0.18405, 0.24464, 0.23398, 0.22002, 0.32884, 0.26896, 0.26573, 0.23583, 0.24367, 0.21461, 0.18046, 0.16081, 0.13592, 0.16508, 0.12901, 0.1477, 0.16122, 0.1068, 0.10555, 0.10078, 0.08805, 0.10271, 0.11352, 0.15741, 0.26014 ], "comparison": { "original": "One", "retranscribed": "One.", "reference_tokens": [ "one" ], "hypothesis_tokens": [ "one" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 1, "reference_words": 1, "hypothesis_words": 1, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "one", "hypothesis": "one", "reference_index": 0, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.69947, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Happy", "emotion_confidence": 0.48141923546791077, "duration_seconds": 1.0409999999999968, "mos": 3.939, "audio_variant": "original", "original_transcript_raw": "Okay okay", "original_transcript": "Okay okay", "retranscribed_transcript": "Okay. Okay.", "backend": "qwen", "emotion_analyzed_seconds": 1.041, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-037", "energy": { "value": 0.515625, "bucket": "low" }, "audio_url": "audio/utterance-037.wav", "spectrogram_url": "spectrograms/utterance-037.png", "waveform": [ 0.19288, 0.19595, 0.19947, 0.2536, 0.22951, 0.2625, 0.20725, 0.21907, 0.23012, 0.21045, 0.19986, 0.21172, 0.2011, 0.25406, 0.25551, 0.24733, 0.25199, 0.22627, 0.28103, 0.23419, 0.24168, 0.24356, 0.23475, 0.2542, 0.2069, 0.23434, 0.21304, 0.24044, 0.21358, 0.21183, 0.20196, 0.19999, 0.22724, 0.20548, 0.20058, 0.19795, 0.19767, 0.20874, 0.19953, 0.18761, 0.19999, 0.20735, 0.18906, 0.20471, 0.19327, 0.18734, 0.20428, 0.19825, 0.19671, 0.14517, 0.14587, 0.09634, 0.07723, 0.05078, 0.02798, 0.03991, 0.04244, 0.0398, 0.02337, 0.02606, 0.04613, 0.03858, 0.02649, 0.02548, 0.0291, 0.03732, 0.03823, 0.02556, 0.02574, 0.02978, 0.04097, 0.03453, 0.05128, 0.03235, 0.04858, 0.05671, 0.04654, 0.02851, 0.03926, 0.06272, 0.09607, 0.13399, 0.14712, 0.17825, 0.18262, 0.19978, 0.18998, 0.20592, 0.22163, 0.23101, 0.237, 0.22211, 0.228, 0.24147, 0.2337, 0.22301, 0.21029, 0.23494, 0.23196, 0.23349, 0.2393, 0.22068, 0.24189, 0.24432, 0.21989, 0.22787, 0.2105, 0.19669, 0.22087, 0.19144, 0.19434, 0.18881, 0.17576, 0.12913, 0.10719, 0.05766, 0.04407, 0.04148, 0.02374, 0.01944, 0.01668, 0.03143, 0.03679, 0.02863, 0.01745, 0.02222, 0.03166, 0.0408, 0.03033, 0.03289, 0.11676, 0.07341, 0.04792, 0.03793, 0.03918, 0.04836, 0.05254, 0.03983, 0.10463, 0.19071, 0.20984, 0.18113, 0.20261, 0.19923, 0.20105, 0.21849, 0.19362, 0.21807, 0.18477, 0.22091, 0.20981, 0.20789, 0.22205, 0.18644, 0.22631, 0.20125, 0.20837, 0.21297, 0.19579, 0.22357, 0.17568, 0.19146, 0.18005, 0.14594, 0.13187, 0.0989, 0.08807, 0.03753, 0.03002, 0.03676, 0.03331, 0.02566, 0.02295, 0.0349, 0.03703, 0.0245, 0.02857, 0.01917, 0.03791, 0.03895 ], "comparison": { "original": "Okay okay", "retranscribed": "Okay. Okay.", "reference_tokens": [ "okay", "okay" ], "hypothesis_tokens": [ "okay", "okay" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 2, "hypothesis_words": 2, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "okay", "hypothesis": "okay", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "okay", "hypothesis": "okay", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.28103, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Happy", "emotion_confidence": 0.5622612237930298, "duration_seconds": 3.165999999999997, "mos": 3.3365, "audio_variant": "original", "original_transcript_raw": "Or through linkedin and we'll be happy to help you. ", "original_transcript": "Or through linkedin and we'll be happy to help you.", "retranscribed_transcript": "Or through LinkedIn, and we'll be happy to help you.", "backend": "qwen", "emotion_analyzed_seconds": 3.166, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-038", "energy": { "value": 0.5, "bucket": "low" }, "audio_url": "audio/utterance-038.wav", "spectrogram_url": "spectrograms/utterance-038.png", "waveform": [ 0.01617, 0.02188, 0.0188, 0.01476, 0.01745, 0.01072, 0.01232, 0.01326, 0.01056, 0.01285, 0.01246, 0.01164, 0.00925, 0.02411, 0.04163, 0.04933, 0.05682, 0.07068, 0.08718, 0.08915, 0.084, 0.09719, 0.10288, 0.0915, 0.0822, 0.06327, 0.03629, 0.02872, 0.04923, 0.03486, 0.06537, 0.17829, 0.22746, 0.22956, 0.23058, 0.1863, 0.14755, 0.06165, 0.0402, 0.02671, 0.02486, 0.02928, 0.03783, 0.02703, 0.02183, 0.06046, 0.11965, 0.10539, 0.10582, 0.09574, 0.06532, 0.07402, 0.06533, 0.08626, 0.06829, 0.16502, 0.13805, 0.14553, 0.11993, 0.11889, 0.09148, 0.07645, 0.05644, 0.03334, 0.0178, 0.01687, 0.01902, 0.0421, 0.19591, 0.13722, 0.18277, 0.16047, 0.13037, 0.14136, 0.15325, 0.13897, 0.12567, 0.0816, 0.06243, 0.06124, 0.03924, 0.02302, 0.01696, 0.00907, 0.01397, 0.00568, 0.00953, 0.01271, 0.00894, 0.01038, 0.01636, 0.01677, 0.02037, 0.01223, 0.00948, 0.00913, 0.01577, 0.01655, 0.00643, 0.02134, 0.01446, 0.02765, 0.05513, 0.14181, 0.10727, 0.16239, 0.14659, 0.16059, 0.17386, 0.14463, 0.14554, 0.14122, 0.09878, 0.06701, 0.06138, 0.06179, 0.06451, 0.05821, 0.0538, 0.04354, 0.04128, 0.02807, 0.03375, 0.08696, 0.13889, 0.13096, 0.14612, 0.13592, 0.08898, 0.05179, 0.04822, 0.03819, 0.07323, 0.09591, 0.08297, 0.09689, 0.11107, 0.04679, 0.0462, 0.05294, 0.08286, 0.16932, 0.18714, 0.13032, 0.03523, 0.02018, 0.01496, 0.08227, 0.07064, 0.03361, 0.01701, 0.01288, 0.01107, 0.02894, 0.03641, 0.04973, 0.02757, 0.02353, 0.01643, 0.02578, 0.04514, 0.07384, 0.08299, 0.0946, 0.04081, 0.02719, 0.01021, 0.00948, 0.00753, 0.00899, 0.01011, 0.01652, 0.03175, 0.0217, 0.03994, 0.01948, 0.01648, 0.01543, 0.01329, 0.00858 ], "comparison": { "original": "Or through linkedin and we'll be happy to help you.", "retranscribed": "Or through LinkedIn, and we'll be happy to help you.", "reference_tokens": [ "or", "through", "linkedin", "and", "well", "be", "happy", "to", "help", "you" ], "hypothesis_tokens": [ "or", "through", "linkedin", "and", "well", "be", "happy", "to", "help", "you" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 10, "reference_words": 10, "hypothesis_words": 10, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "or", "hypothesis": "or", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "through", "hypothesis": "through", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "linkedin", "hypothesis": "linkedin", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "well", "hypothesis": "well", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "be", "hypothesis": "be", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "happy", "hypothesis": "happy", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "help", "hypothesis": "help", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 9, "hypothesis_index": 9 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.23058, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Happy", "emotion_confidence": 0.4290950894355774, "duration_seconds": 6.023999999999999, "mos": 3.8203, "audio_variant": "original", "original_transcript_raw": "He says, i've heard your prayers, i've seen your tears, you're going to have a son. I have great plans for him. ", "original_transcript": "He says, i've heard your prayers, i've seen your tears, you're going to have a son. I have great plans for him.", "retranscribed_transcript": "He says, \"I've heard your prayers. I've seen your tears. You're going to have a son. I have great plans for him.\"", "backend": "qwen", "emotion_analyzed_seconds": 6.024, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-039", "energy": { "value": 0.49609375, "bucket": "low" }, "audio_url": "audio/utterance-039.wav", "spectrogram_url": "spectrograms/utterance-039.png", "waveform": [ 0.02725, 0.07946, 0.07519, 0.0398, 0.0479, 0.02808, 0.19319, 0.22392, 0.22509, 0.19283, 0.15729, 0.06205, 0.06888, 0.05127, 0.02952, 0.02094, 0.00356, 0.00106, 0.00977, 0.04549, 0.24606, 0.35852, 0.29247, 0.16673, 0.05429, 0.04733, 0.04515, 0.02854, 0.02384, 0.13573, 0.24542, 0.25541, 0.22835, 0.21715, 0.07056, 0.0466, 0.08053, 0.11031, 0.15175, 0.18536, 0.14153, 0.04638, 0.02237, 0.00275, 0.00238, 0.02054, 0.01921, 0.17485, 0.27225, 0.29488, 0.29128, 0.27322, 0.26336, 0.23256, 0.19049, 0.14159, 0.03506, 0.03462, 0.11472, 0.16324, 0.17228, 0.05227, 0.04484, 0.0374, 0.05314, 0.04219, 0.04163, 0.12875, 0.17806, 0.20492, 0.19156, 0.14643, 0.10845, 0.10895, 0.14892, 0.14529, 0.22292, 0.24505, 0.21933, 0.16927, 0.06103, 0.01155, 0.0063, 0.05045, 0.03112, 0.01913, 0.04363, 0.17311, 0.2725, 0.32395, 0.37584, 0.36875, 0.35155, 0.35021, 0.31216, 0.24084, 0.20748, 0.15959, 0.11509, 0.05156, 0.04941, 0.05787, 0.05448, 0.04082, 0.0189, 0.03383, 0.12553, 0.26053, 0.25593, 0.14905, 0.05849, 0.17564, 0.24981, 0.26764, 0.19477, 0.07828, 0.25807, 0.36506, 0.3374, 0.33556, 0.08569, 0.18114, 0.17072, 0.0681, 0.06099, 0.05327, 0.0333, 0.05232, 0.26367, 0.31794, 0.31449, 0.27026, 0.24759, 0.28993, 0.25061, 0.18445, 0.17811, 0.2025, 0.15032, 0.08526, 0.04795, 0.04697, 0.24955, 0.35241, 0.39426, 0.28139, 0.04068, 0.01566, 0.02257, 0.03378, 0.0113, 0.19743, 0.21703, 0.20014, 0.2239, 0.22662, 0.20647, 0.18761, 0.1567, 0.07709, 0.05666, 0.03243, 0.02214, 0.13151, 0.11645, 0.02694, 0.03179, 0.10685, 0.15969, 0.18681, 0.24326, 0.22534, 0.2072, 0.1031, 0.07777, 0.07723, 0.06621, 0.04187, 0.02683, 0.0056 ], "comparison": { "original": "He says, i've heard your prayers, i've seen your tears, you're going to have a son. I have great plans for him.", "retranscribed": "He says, \"I've heard your prayers. I've seen your tears. You're going to have a son. I have great plans for him.\"", "reference_tokens": [ "he", "says", "ive", "heard", "your", "prayers", "ive", "seen", "your", "tears", "youre", "going", "to", "have", "a", "son", "i", "have", "great", "plans", "for", "him" ], "hypothesis_tokens": [ "he", "says", "ive", "heard", "your", "prayers", "ive", "seen", "your", "tears", "youre", "going", "to", "have", "a", "son", "i", "have", "great", "plans", "for", "him" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 22, "reference_words": 22, "hypothesis_words": 22, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "he", "hypothesis": "he", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "says", "hypothesis": "says", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "ive", "hypothesis": "ive", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "heard", "hypothesis": "heard", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "your", "hypothesis": "your", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "prayers", "hypothesis": "prayers", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "ive", "hypothesis": "ive", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "seen", "hypothesis": "seen", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "your", "hypothesis": "your", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "tears", "hypothesis": "tears", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "youre", "hypothesis": "youre", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "going", "hypothesis": "going", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "have", "hypothesis": "have", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "son", "hypothesis": "son", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "have", "hypothesis": "have", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "great", "hypothesis": "great", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "plans", "hypothesis": "plans", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "for", "hypothesis": "for", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "him", "hypothesis": "him", "reference_index": 21, "hypothesis_index": 21 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.39426, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Happy", "emotion_confidence": 0.2696537971496582, "duration_seconds": 1.1429999999999865, "mos": 3.1415, "audio_variant": "original", "original_transcript_raw": "You saved me. ", "original_transcript": "You saved me.", "retranscribed_transcript": "You saved me.", "backend": "qwen", "emotion_analyzed_seconds": 1.143, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-040", "energy": { "value": 0.54296875, "bucket": "medium" }, "audio_url": "audio/utterance-040.wav", "spectrogram_url": "spectrograms/utterance-040.png", "waveform": [ 0.02514, 0.02712, 0.01738, 0.0189, 0.02257, 0.0325, 0.02231, 0.01837, 0.02712, 0.0198, 0.02039, 0.01868, 0.01884, 0.02228, 0.03102, 0.01638, 0.02354, 0.01974, 0.02963, 0.03109, 0.03056, 0.04627, 0.05312, 0.05446, 0.06552, 0.05845, 0.06973, 0.08453, 0.083, 0.09091, 0.10272, 0.14445, 0.12142, 0.12658, 0.10514, 0.11369, 0.10019, 0.1105, 0.09362, 0.09803, 0.07521, 0.07715, 0.06005, 0.05836, 0.07967, 0.06076, 0.06809, 0.05913, 0.06772, 0.06385, 0.07369, 0.0377, 0.05121, 0.06452, 0.07954, 0.04055, 0.04573, 0.04106, 0.03291, 0.05037, 0.07581, 0.06043, 0.06545, 0.07959, 0.06702, 0.10841, 0.16612, 0.13488, 0.15722, 0.1504, 0.17304, 0.18457, 0.18352, 0.15812, 0.17261, 0.14243, 0.16633, 0.12466, 0.14333, 0.13089, 0.13294, 0.13481, 0.16459, 0.15648, 0.14373, 0.13074, 0.13826, 0.05073, 0.06479, 0.05505, 0.07164, 0.05806, 0.05753, 0.07096, 0.07921, 0.09638, 0.09538, 0.05254, 0.05188, 0.05246, 0.05828, 0.05134, 0.04889, 0.05226, 0.05062, 0.07485, 0.0727, 0.1091, 0.13322, 0.10808, 0.16611, 0.12331, 0.12487, 0.11981, 0.11104, 0.10197, 0.14268, 0.11862, 0.10369, 0.07769, 0.08877, 0.09099, 0.09821, 0.09168, 0.07965, 0.07733, 0.0553, 0.06019, 0.05381, 0.04956, 0.06281, 0.06538, 0.06452, 0.03883, 0.05008, 0.0547, 0.04312, 0.03704, 0.03593, 0.05477, 0.03769, 0.04179, 0.03877, 0.03226, 0.03521, 0.02185, 0.02753, 0.03105, 0.02251, 0.02741, 0.02807, 0.02758, 0.02909, 0.03406, 0.02535, 0.02062, 0.03358, 0.04026, 0.04277, 0.02833, 0.04254, 0.03902, 0.03294, 0.02723, 0.02608, 0.02369, 0.02529, 0.03408, 0.03632, 0.03154, 0.03725, 0.02583, 0.02366, 0.0322, 0.03639, 0.03043, 0.0276, 0.03617, 0.03389, 0.02886 ], "comparison": { "original": "You saved me.", "retranscribed": "You saved me.", "reference_tokens": [ "you", "saved", "me" ], "hypothesis_tokens": [ "you", "saved", "me" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 3, "reference_words": 3, "hypothesis_words": 3, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "saved", "hypothesis": "saved", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.18457, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Happy", "emotion_confidence": 0.46384197473526, "duration_seconds": 2.730000000000004, "mos": 3.2942, "audio_variant": "original", "original_transcript_raw": "I got a feeling those two gonna need some time alone tonight. ", "original_transcript": "I got a feeling those two gonna need some time alone tonight.", "retranscribed_transcript": "I got a feeling those two gonna need some time alone tonight.", "backend": "qwen", "emotion_analyzed_seconds": 2.73, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-041", "energy": { "value": 0.57421875, "bucket": "medium" }, "audio_url": "audio/utterance-041.wav", "spectrogram_url": "spectrograms/utterance-041.png", "waveform": [ 0.11766, 0.18394, 0.21317, 0.26214, 0.31702, 0.32343, 0.35907, 0.34608, 0.32175, 0.36232, 0.34719, 0.0819, 0.06889, 0.0778, 0.2617, 0.46201, 0.47356, 0.44971, 0.35154, 0.35578, 0.32558, 0.21995, 0.13408, 0.27629, 0.28195, 0.25913, 0.06732, 0.04794, 0.02089, 0.02085, 0.01898, 0.01823, 0.0901, 0.28798, 0.28491, 0.30307, 0.30155, 0.27054, 0.15116, 0.12386, 0.12124, 0.23232, 0.20437, 0.20005, 0.17256, 0.15184, 0.11732, 0.10967, 0.09451, 0.09662, 0.08991, 0.19184, 0.18222, 0.1867, 0.20609, 0.25544, 0.26904, 0.21424, 0.16353, 0.13601, 0.06572, 0.04824, 0.043, 0.04077, 0.02655, 0.02865, 0.03346, 0.02387, 0.07242, 0.16367, 0.17865, 0.15993, 0.13312, 0.11432, 0.10113, 0.09971, 0.076, 0.05097, 0.03702, 0.04308, 0.11444, 0.15422, 0.16785, 0.17634, 0.17366, 0.15551, 0.13202, 0.11131, 0.08688, 0.08043, 0.07944, 0.07325, 0.06727, 0.1352, 0.14423, 0.15739, 0.1576, 0.17482, 0.17372, 0.14742, 0.10363, 0.0489, 0.0353, 0.04344, 0.02473, 0.02263, 0.0197, 0.01587, 0.04503, 0.03845, 0.0462, 0.04546, 0.039, 0.03027, 0.01688, 0.02373, 0.02519, 0.13253, 0.17307, 0.17696, 0.23222, 0.27653, 0.31423, 0.26824, 0.29531, 0.26781, 0.08205, 0.06653, 0.06914, 0.10597, 0.17476, 0.12165, 0.1152, 0.10224, 0.0851, 0.07578, 0.0761, 0.11055, 0.37555, 0.35749, 0.32307, 0.20204, 0.1874, 0.09883, 0.09163, 0.09929, 0.07143, 0.08381, 0.06423, 0.03703, 0.04155, 0.02379, 0.02065, 0.01659, 0.01259, 0.01762, 0.01857, 0.03562, 0.04873, 0.05319, 0.05499, 0.05112, 0.0588, 0.0777, 0.06002, 0.05552, 0.06447, 0.04403, 0.03358, 0.01828, 0.02165, 0.01175, 0.00857, 0.00514, 0.00579, 0.00403, 0.00499, 0.00483, 0.00366, 0.00444 ], "comparison": { "original": "I got a feeling those two gonna need some time alone tonight.", "retranscribed": "I got a feeling those two gonna need some time alone tonight.", "reference_tokens": [ "i", "got", "a", "feeling", "those", "two", "gonna", "need", "some", "time", "alone", "tonight" ], "hypothesis_tokens": [ "i", "got", "a", "feeling", "those", "two", "gonna", "need", "some", "time", "alone", "tonight" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 12, "reference_words": 12, "hypothesis_words": 12, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "got", "hypothesis": "got", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "feeling", "hypothesis": "feeling", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "those", "hypothesis": "those", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "two", "hypothesis": "two", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "gonna", "hypothesis": "gonna", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "need", "hypothesis": "need", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "some", "hypothesis": "some", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "time", "hypothesis": "time", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "alone", "hypothesis": "alone", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "tonight", "hypothesis": "tonight", "reference_index": 11, "hypothesis_index": 11 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.47356, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Happy", "emotion_confidence": 0.7222884893417358, "duration_seconds": 1.382000000000005, "mos": 3.4492, "audio_variant": "original", "original_transcript_raw": "Yeah, thank you for watching. ", "original_transcript": "Yeah, thank you for watching.", "retranscribed_transcript": "Yeah. Thank you for watching.", "backend": "qwen", "emotion_analyzed_seconds": 1.382, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-042", "energy": { "value": 0.51953125, "bucket": "medium" }, "audio_url": "audio/utterance-042.wav", "spectrogram_url": "spectrograms/utterance-042.png", "waveform": [ 0.00297, 0.02485, 0.05533, 0.05402, 0.08622, 0.12065, 0.1693, 0.54992, 0.69828, 0.74276, 0.7126, 0.56169, 0.49451, 0.51941, 0.61152, 0.56941, 0.5228, 0.48568, 0.4664, 0.49825, 0.39626, 0.35828, 0.24427, 0.19247, 0.20493, 0.17094, 0.1328, 0.19135, 0.11236, 0.12295, 0.09976, 0.10803, 0.05923, 0.05837, 0.04786, 0.05461, 0.05764, 0.03813, 0.03701, 0.04218, 0.03478, 0.03414, 0.03062, 0.03245, 0.01667, 0.0143, 0.01505, 0.01377, 0.01367, 0.01184, 0.00996, 0.00448, 0.00701, 0.00701, 0.00402, 0.00275, 0.00282, 0.00367, 0.004, 0.0055, 0.022, 0.01207, 0.06368, 0.04577, 0.21789, 0.71779, 1.0393, 1.01636, 0.83345, 0.74967, 0.6979, 0.66718, 0.52436, 0.36459, 0.34984, 0.31264, 0.32838, 0.34454, 0.22883, 0.20419, 0.12701, 0.12049, 0.10563, 0.18719, 0.24388, 0.37936, 0.46087, 0.55561, 0.5926, 0.57785, 0.50414, 0.46146, 0.33788, 0.22296, 0.15195, 0.11989, 0.07227, 0.04721, 0.05473, 0.09558, 0.04739, 0.03856, 0.23499, 0.46219, 0.49162, 0.50383, 0.51154, 0.42094, 0.49459, 0.52122, 0.61765, 0.57569, 0.60904, 0.54413, 0.45588, 0.37422, 0.37965, 0.46122, 0.32251, 0.57084, 0.72846, 0.4184, 0.51181, 0.36385, 0.36054, 0.32146, 0.2478, 0.42214, 0.3658, 0.18733, 0.19074, 0.09228, 0.05719, 0.04172, 0.03401, 0.03422, 0.04024, 0.06961, 0.0635, 0.06461, 0.05413, 0.05415, 0.14236, 0.22848, 0.24728, 0.11572, 0.2092, 0.12529, 0.20648, 0.20777, 0.10696, 0.19258, 0.11356, 0.17007, 0.10684, 0.06696, 0.10963, 0.06629, 0.08991, 0.10593, 0.03936, 0.06441, 0.06471, 0.08028, 0.05981, 0.07469, 0.06043, 0.03706, 0.06075, 0.04714, 0.05615, 0.05808, 0.03692, 0.01951, 0.01377, 0.01144, 0.00915, 0.00674, 0.00728, 0.00742 ], "comparison": { "original": "Yeah, thank you for watching.", "retranscribed": "Yeah. Thank you for watching.", "reference_tokens": [ "yeah", "thank", "you", "for", "watching" ], "hypothesis_tokens": [ "yeah", "thank", "you", "for", "watching" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "yeah", "hypothesis": "yeah", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "thank", "hypothesis": "thank", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "for", "hypothesis": "for", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "watching", "hypothesis": "watching", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz float32 WAV", "source_peak_abs": 1.0393, "audio_sample_format": "float32" }, { "language": "English", "emotion": "Happy", "emotion_confidence": 0.8598352074623108, "duration_seconds": 1.0409999999999968, "mos": 3.0399, "audio_variant": "original", "original_transcript_raw": "Absolutely", "original_transcript": "Absolutely", "retranscribed_transcript": "Absolutely.", "backend": "qwen", "emotion_analyzed_seconds": 1.041, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-043", "energy": { "value": 0.65234375, "bucket": "high" }, "audio_url": "audio/utterance-043.wav", "spectrogram_url": "spectrograms/utterance-043.png", "waveform": [ 0.02225, 0.11319, 0.18497, 0.15366, 0.2553, 0.17081, 0.23406, 0.17489, 0.17402, 0.1865, 0.19216, 0.23362, 0.16848, 0.12484, 0.38188, 0.42253, 0.29586, 0.14331, 0.10144, 0.09093, 0.08839, 0.07211, 0.06069, 0.07718, 0.07114, 0.06075, 0.06533, 0.0517, 0.05832, 0.0656, 0.08042, 0.05998, 0.10812, 0.16854, 0.22519, 0.18324, 0.25877, 0.27648, 0.11238, 0.13682, 0.14555, 0.12888, 0.11585, 0.10083, 0.11348, 0.14201, 0.12783, 0.12469, 0.11682, 0.09491, 0.12774, 0.09847, 0.08689, 0.08335, 0.03086, 0.04712, 0.05915, 0.05043, 0.05401, 0.0669, 0.04855, 0.07132, 0.07433, 0.07415, 0.10469, 0.097, 0.07369, 0.0768, 0.06607, 0.04608, 0.03173, 0.02419, 0.02759, 0.06985, 0.12066, 0.15096, 0.14071, 0.15298, 0.12282, 0.11064, 0.13995, 0.22151, 0.14487, 0.10351, 0.11454, 0.10887, 0.16852, 0.14748, 0.17052, 0.18911, 0.18317, 0.19059, 0.22408, 0.18498, 0.1883, 0.19654, 0.1922, 0.18269, 0.19639, 0.23648, 0.26545, 0.29891, 0.27914, 0.23856, 0.23949, 0.24241, 0.22106, 0.20092, 0.20225, 0.19938, 0.19443, 0.2005, 0.17703, 0.22592, 0.26029, 0.25612, 0.25506, 0.2028, 0.08493, 0.08612, 0.05437, 0.07758, 0.09812, 0.06986, 0.05257, 0.03433, 0.02504, 0.03013, 0.0445, 0.03289, 0.02362, 0.02699, 0.02748, 0.02474, 0.04032, 0.05227, 0.03926, 0.04653, 0.06457, 0.12297, 0.11762, 0.06243, 0.08065, 0.09697, 0.06309, 0.08082, 0.09797, 0.10311, 0.08942, 0.09966, 0.07934, 0.09405, 0.08396, 0.08305, 0.05285, 0.04058, 0.04046, 0.02039, 0.01909, 0.0123, 0.01518, 0.02312, 0.01602, 0.00955, 0.0088, 0.00788, 0.00754, 0.00994, 0.00675, 0.00246, 0.00422, 0.00335, 0.00348, 0.003, 0.00209, 0.00129, 0.00227, 0.0119, 0.00817, 0.0026 ], "comparison": { "original": "Absolutely", "retranscribed": "Absolutely.", "reference_tokens": [ "absolutely" ], "hypothesis_tokens": [ "absolutely" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 1, "reference_words": 1, "hypothesis_words": 1, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "absolutely", "hypothesis": "absolutely", "reference_index": 0, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.42253, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Happy", "emotion_confidence": 0.5731147527694702, "duration_seconds": 1.620999999999981, "mos": 3.2751, "audio_variant": "cleaned", "original_transcript_raw": "Sí, here comes a mí. ", "original_transcript": "Sí, here comes a mí.", "retranscribed_transcript": "See here comes the move.", "backend": "qwen", "emotion_analyzed_seconds": 1.621, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-044", "energy": { "value": 0.671875, "bucket": "high" }, "audio_url": "audio/utterance-044.wav", "spectrogram_url": "spectrograms/utterance-044.png", "waveform": [ 0.16304, 0.11865, 0.08933, 0.06751, 0.03803, 0.01281, 0.00991, 0.01045, 0.0108, 0.00983, 0.01409, 0.02017, 0.0169, 0.02118, 0.02062, 0.01785, 0.06286, 0.07942, 0.08814, 0.0966, 0.10522, 0.1066, 0.09269, 0.10153, 0.09153, 0.07989, 0.07815, 0.07688, 0.06978, 0.0739, 0.07861, 0.0664, 0.06443, 0.05973, 0.05531, 0.05201, 0.05969, 0.04903, 0.04593, 0.04338, 0.059, 0.04995, 0.05689, 0.05209, 0.0557, 0.05895, 0.04335, 0.04096, 0.04363, 0.05319, 0.03899, 0.04597, 0.035, 0.0475, 0.05555, 0.05566, 0.05906, 0.07659, 0.06936, 0.06338, 0.06843, 0.06668, 0.06142, 0.07515, 0.07799, 0.05042, 0.04797, 0.03998, 0.03926, 0.03801, 0.03635, 0.02925, 0.02588, 0.01971, 0.0182, 0.01796, 0.01562, 0.0171, 0.01221, 0.01683, 0.01479, 0.10214, 0.15034, 0.18594, 0.19472, 0.22538, 0.26059, 0.29866, 0.30256, 0.30599, 0.33665, 0.31399, 0.31922, 0.31919, 0.30122, 0.33417, 0.34712, 0.35915, 0.3554, 0.33338, 0.26025, 0.1985, 0.19928, 0.15703, 0.06668, 0.00818, 0.00567, 0.00227, 0.00179, 0.11268, 0.18577, 0.15416, 0.07188, 0.09179, 0.19109, 0.23452, 0.29793, 0.31778, 0.3408, 0.33953, 0.30433, 0.2064, 0.14197, 0.09669, 0.06484, 0.06306, 0.09281, 0.09943, 0.09674, 0.08275, 0.06704, 0.06598, 0.04407, 0.03896, 0.05847, 0.076, 0.11275, 0.15923, 0.12904, 0.14056, 0.13413, 0.12466, 0.09623, 0.06756, 0.07417, 0.07738, 0.07507, 0.08419, 0.09829, 0.09898, 0.09921, 0.08741, 0.08233, 0.08245, 0.07823, 0.08265, 0.18295, 0.14682, 0.13464, 0.09996, 0.09912, 0.09351, 0.09154, 0.06296, 0.06196, 0.05086, 0.05308, 0.05128, 0.04445, 0.04208, 0.02932, 0.02402, 0.01667, 0.01253, 0.01021, 0.01866, 0.01993, 0.06446, 0.08704, 0.07043 ], "comparison": { "original": "Sí, here comes a mí.", "retranscribed": "See here comes the move.", "reference_tokens": [ "sí", "here", "comes", "a", "mí" ], "hypothesis_tokens": [ "see", "here", "comes", "the", "move" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 5, "hypothesis_words": 5, "edits": 3 }, "wer": 0.6, "wer_percent": 60.0, "alignment": [ { "op": "substitute", "reference": "sí", "hypothesis": "see", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "here", "hypothesis": "here", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "comes", "hypothesis": "comes", "reference_index": 2, "hypothesis_index": 2 }, { "op": "substitute", "reference": "a", "hypothesis": "the", "reference_index": 3, "hypothesis_index": 3 }, { "op": "substitute", "reference": "mí", "hypothesis": "move", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.35915, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Happy", "emotion_confidence": 0.6481068134307861, "duration_seconds": 0.6319999999999766, "mos": 3.3831, "audio_variant": "cleaned", "original_transcript_raw": "Girl", "original_transcript": "Girl", "retranscribed_transcript": "Girl.", "backend": "qwen", "emotion_analyzed_seconds": 0.632, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-045", "energy": { "value": 0.6796875, "bucket": "high" }, "audio_url": "audio/utterance-045.wav", "spectrogram_url": "spectrograms/utterance-045.png", "waveform": [ 0.1824, 0.18501, 0.16857, 0.14635, 0.14262, 0.14136, 0.12647, 0.1026, 0.08175, 0.07452, 0.04544, 0.03028, 0.01581, 0.00626, 0.00114, 0.00086, 0.00097, 0.00062, 0.00041, 0.0006, 0.00065, 0.00041, 0.00073, 0.00042, 0.00061, 0.00198, 0.002, 0.00212, 0.00424, 0.00408, 0.0042, 0.00342, 0.00512, 0.00631, 0.0075, 0.00542, 0.005, 0.01024, 0.00696, 0.01143, 0.02004, 0.04666, 0.05713, 0.07959, 0.10803, 0.09921, 0.0664, 0.04978, 0.09668, 0.07385, 0.12401, 0.1132, 0.11797, 0.11122, 0.10369, 0.09918, 0.1002, 0.10056, 0.09717, 0.10421, 0.12728, 0.13628, 0.14444, 0.15035, 0.15155, 0.1311, 0.14105, 0.14205, 0.14384, 0.14698, 0.14347, 0.11656, 0.16869, 0.16345, 0.14747, 0.14354, 0.13423, 0.17119, 0.16711, 0.16862, 0.19086, 0.18175, 0.21011, 0.24255, 0.26553, 0.24413, 0.23276, 0.1495, 0.23917, 0.18311, 0.16065, 0.17016, 0.14311, 0.18834, 0.18108, 0.18289, 0.17126, 0.16934, 0.17394, 0.14429, 0.17372, 0.13412, 0.0682, 0.14279, 0.16837, 0.15229, 0.16165, 0.15707, 0.16788, 0.13404, 0.15342, 0.16251, 0.15425, 0.15264, 0.18213, 0.18835, 0.19106, 0.18255, 0.19659, 0.18558, 0.15622, 0.14266, 0.13406, 0.13218, 0.15735, 0.13424, 0.08053, 0.10775, 0.0541, 0.06526, 0.03364, 0.02466, 0.0194, 0.02066, 0.01332, 0.01235, 0.01538, 0.01207, 0.01814, 0.01089, 0.00711, 0.00698, 0.00791, 0.00457, 0.00641, 0.00568, 0.00393, 0.00285, 0.00195, 0.00318, 0.00271, 0.00301, 0.00226, 0.00174, 0.00161, 0.00083, 0.00061, 0.0011, 0.00062, 0.00114, 0.00065, 0.00034, 0.00056, 0.00059, 0.00048, 0.00075, 0.00477, 0.0092, 0.01676, 0.02826, 0.03765, 0.07097, 0.06104, 0.05112, 0.06027, 0.09003, 0.11791, 0.11358, 0.09674, 0.08832 ], "comparison": { "original": "Girl", "retranscribed": "Girl.", "reference_tokens": [ "girl" ], "hypothesis_tokens": [ "girl" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 1, "reference_words": 1, "hypothesis_words": 1, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "girl", "hypothesis": "girl", "reference_index": 0, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.26553, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Neutral", "emotion_confidence": 0.78556889295578, "duration_seconds": 17.52600000000001, "mos": 3.0273, "audio_variant": "original", "original_transcript_raw": "Supporters gathered outside meanwhile one of the party's liberal stalwarts, a man by the name of lev schlossberg, is widely expected to be convicted and sentenced to a long prison term today. The formal charge against schlossberg is denigrating the russian army, although his supporters would say he's being punished for his passivism and that his case is. ", "original_transcript": "Supporters gathered outside meanwhile one of the party's liberal stalwarts, a man by the name of lev schlossberg, is widely expected to be convicted and sentenced to a long prison term today. The formal charge against schlossberg is denigrating the russian army, although his supporters would say he's being punished for his passivism and that his case is.", "retranscribed_transcript": "Supporters gathered outside. Meanwhile, one of the party's liberal stalwarts, a man by the name of Lev Schlossberg, is widely expected to be convicted and sentenced to a long prison term today. The formal charge against Schlossberg is denigrating the Russian army, although his supporters would say he's being punished for his pacifism, and that his case is.", "backend": "qwen", "emotion_analyzed_seconds": 17.526, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-046", "energy": { "value": 0.46875, "bucket": "low" }, "audio_url": "audio/utterance-046.wav", "spectrogram_url": "spectrograms/utterance-046.png", "waveform": [ 0.17755, 0.17344, 0.13472, 0.17993, 0.18853, 0.13763, 0.15061, 0.17443, 0.18397, 0.05593, 0.19884, 0.13757, 0.12381, 0.09907, 0.05831, 0.09656, 0.05836, 0.17435, 0.17287, 0.13599, 0.12579, 0.13918, 0.13754, 0.1609, 0.08959, 0.22951, 0.12675, 0.11823, 0.14593, 0.16184, 0.14632, 0.07213, 0.25377, 0.12656, 0.12256, 0.14053, 0.05983, 0.20757, 0.15218, 0.14009, 0.18574, 0.14613, 0.12965, 0.13224, 0.14202, 0.07979, 0.15146, 0.14467, 0.07789, 0.09843, 0.14858, 0.15553, 0.09183, 0.1837, 0.16361, 0.09067, 0.16297, 0.13424, 0.20965, 0.16771, 0.12023, 0.1208, 0.17653, 0.23792, 0.15368, 0.17237, 0.12135, 0.1059, 0.13988, 0.14634, 0.1604, 0.17042, 0.17171, 0.10557, 0.05538, 0.16124, 0.13052, 0.12303, 0.12237, 0.07491, 0.16198, 0.13715, 0.14623, 0.09547, 0.17468, 0.19682, 0.11169, 0.07378, 0.17288, 0.14089, 0.14088, 0.08834, 0.15133, 0.1419, 0.12759, 0.05492, 0.06689, 0.05669, 0.04102, 0.19903, 0.13649, 0.16258, 0.13171, 0.07585, 0.18116, 0.15986, 0.12496, 0.16501, 0.10619, 0.14606, 0.14892, 0.09888, 0.22117, 0.1769, 0.12119, 0.10734, 0.06469, 0.19168, 0.17719, 0.11987, 0.15305, 0.11961, 0.11407, 0.19323, 0.07159, 0.16425, 0.15961, 0.15064, 0.11283, 0.11705, 0.14491, 0.14678, 0.14432, 0.13231, 0.05152, 0.09751, 0.19042, 0.16516, 0.13329, 0.05553, 0.16367, 0.06188, 0.16465, 0.13393, 0.02896, 0.1409, 0.11667, 0.15558, 0.13313, 0.21696, 0.22296, 0.14927, 0.05389, 0.21255, 0.16366, 0.14166, 0.20062, 0.19127, 0.13257, 0.14948, 0.12969, 0.15012, 0.13557, 0.07393, 0.06978, 0.06139, 0.04547, 0.03757, 0.1832, 0.19829, 0.13384, 0.0946, 0.09555, 0.15585, 0.12593, 0.09834, 0.10527, 0.12754, 0.14638, 0.14368 ], "comparison": { "original": "Supporters gathered outside meanwhile one of the party's liberal stalwarts, a man by the name of lev schlossberg, is widely expected to be convicted and sentenced to a long prison term today. The formal charge against schlossberg is denigrating the russian army, although his supporters would say he's being punished for his passivism and that his case is.", "retranscribed": "Supporters gathered outside. Meanwhile, one of the party's liberal stalwarts, a man by the name of Lev Schlossberg, is widely expected to be convicted and sentenced to a long prison term today. The formal charge against Schlossberg is denigrating the Russian army, although his supporters would say he's being punished for his pacifism, and that his case is.", "reference_tokens": [ "supporters", "gathered", "outside", "meanwhile", "one", "of", "the", "partys", "liberal", "stalwarts", "a", "man", "by", "the", "name", "of", "lev", "schlossberg", "is", "widely", "expected", "to", "be", "convicted", "and", "sentenced", "to", "a", "long", "prison", "term", "today", "the", "formal", "charge", "against", "schlossberg", "is", "denigrating", "the", "russian", "army", "although", "his", "supporters", "would", "say", "hes", "being", "punished", "for", "his", "passivism", "and", "that", "his", "case", "is" ], "hypothesis_tokens": [ "supporters", "gathered", "outside", "meanwhile", "one", "of", "the", "partys", "liberal", "stalwarts", "a", "man", "by", "the", "name", "of", "lev", "schlossberg", "is", "widely", "expected", "to", "be", "convicted", "and", "sentenced", "to", "a", "long", "prison", "term", "today", "the", "formal", "charge", "against", "schlossberg", "is", "denigrating", "the", "russian", "army", "although", "his", "supporters", "would", "say", "hes", "being", "punished", "for", "his", "pacifism", "and", "that", "his", "case", "is" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 57, "reference_words": 58, "hypothesis_words": 58, "edits": 1 }, "wer": 0.017241379310344827, "wer_percent": 1.7241379310344827, "alignment": [ { "op": "equal", "reference": "supporters", "hypothesis": "supporters", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "gathered", "hypothesis": "gathered", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "outside", "hypothesis": "outside", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "meanwhile", "hypothesis": "meanwhile", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "one", "hypothesis": "one", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "partys", "hypothesis": "partys", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "liberal", "hypothesis": "liberal", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "stalwarts", "hypothesis": "stalwarts", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "man", "hypothesis": "man", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "by", "hypothesis": "by", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "name", "hypothesis": "name", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "lev", "hypothesis": "lev", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "schlossberg", "hypothesis": "schlossberg", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "is", "hypothesis": "is", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "widely", "hypothesis": "widely", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "expected", "hypothesis": "expected", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "be", "hypothesis": "be", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "convicted", "hypothesis": "convicted", "reference_index": 23, "hypothesis_index": 23 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 24, "hypothesis_index": 24 }, { "op": "equal", "reference": "sentenced", "hypothesis": "sentenced", "reference_index": 25, "hypothesis_index": 25 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 26, "hypothesis_index": 26 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 27, "hypothesis_index": 27 }, { "op": "equal", "reference": "long", "hypothesis": "long", "reference_index": 28, "hypothesis_index": 28 }, { "op": "equal", "reference": "prison", "hypothesis": "prison", "reference_index": 29, "hypothesis_index": 29 }, { "op": "equal", "reference": "term", "hypothesis": "term", "reference_index": 30, "hypothesis_index": 30 }, { "op": "equal", "reference": "today", "hypothesis": "today", "reference_index": 31, "hypothesis_index": 31 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 32, "hypothesis_index": 32 }, { "op": "equal", "reference": "formal", "hypothesis": "formal", "reference_index": 33, "hypothesis_index": 33 }, { "op": "equal", "reference": "charge", "hypothesis": "charge", "reference_index": 34, "hypothesis_index": 34 }, { "op": "equal", "reference": "against", "hypothesis": "against", "reference_index": 35, "hypothesis_index": 35 }, { "op": "equal", "reference": "schlossberg", "hypothesis": "schlossberg", "reference_index": 36, "hypothesis_index": 36 }, { "op": "equal", "reference": "is", "hypothesis": "is", "reference_index": 37, "hypothesis_index": 37 }, { "op": "equal", "reference": "denigrating", "hypothesis": "denigrating", "reference_index": 38, "hypothesis_index": 38 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 39, "hypothesis_index": 39 }, { "op": "equal", "reference": "russian", "hypothesis": "russian", "reference_index": 40, "hypothesis_index": 40 }, { "op": "equal", "reference": "army", "hypothesis": "army", "reference_index": 41, "hypothesis_index": 41 }, { "op": "equal", "reference": "although", "hypothesis": "although", "reference_index": 42, "hypothesis_index": 42 }, { "op": "equal", "reference": "his", "hypothesis": "his", "reference_index": 43, "hypothesis_index": 43 }, { "op": "equal", "reference": "supporters", "hypothesis": "supporters", "reference_index": 44, "hypothesis_index": 44 }, { "op": "equal", "reference": "would", "hypothesis": "would", "reference_index": 45, "hypothesis_index": 45 }, { "op": "equal", "reference": "say", "hypothesis": "say", "reference_index": 46, "hypothesis_index": 46 }, { "op": "equal", "reference": "hes", "hypothesis": "hes", "reference_index": 47, "hypothesis_index": 47 }, { "op": "equal", "reference": "being", "hypothesis": "being", "reference_index": 48, "hypothesis_index": 48 }, { "op": "equal", "reference": "punished", "hypothesis": "punished", "reference_index": 49, "hypothesis_index": 49 }, { "op": "equal", "reference": "for", "hypothesis": "for", "reference_index": 50, "hypothesis_index": 50 }, { "op": "equal", "reference": "his", "hypothesis": "his", "reference_index": 51, "hypothesis_index": 51 }, { "op": "substitute", "reference": "passivism", "hypothesis": "pacifism", "reference_index": 52, "hypothesis_index": 52 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 53, "hypothesis_index": 53 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 54, "hypothesis_index": 54 }, { "op": "equal", "reference": "his", "hypothesis": "his", "reference_index": 55, "hypothesis_index": 55 }, { "op": "equal", "reference": "case", "hypothesis": "case", "reference_index": 56, "hypothesis_index": 56 }, { "op": "equal", "reference": "is", "hypothesis": "is", "reference_index": 57, "hypothesis_index": 57 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.25377, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Neutral", "emotion_confidence": 0.8461446762084961, "duration_seconds": 5.836000000000013, "mos": 3.5723, "audio_variant": "original", "original_transcript_raw": "Third, we see the bible as a living text where the holy spirit speaks to us today. ", "original_transcript": "Third, we see the bible as a living text where the holy spirit speaks to us today.", "retranscribed_transcript": "Third, we see the Bible as a living text where the Holy Spirit speaks to us today.", "backend": "qwen", "emotion_analyzed_seconds": 5.836, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-047", "energy": { "value": 0.42578125, "bucket": "low" }, "audio_url": "audio/utterance-047.wav", "spectrogram_url": "spectrograms/utterance-047.png", "waveform": [ 0.02411, 0.02805, 0.05727, 0.05898, 0.4561, 0.47867, 0.48974, 0.43294, 0.34437, 0.34523, 0.3439, 0.27706, 0.27554, 0.2399, 0.07453, 0.12808, 0.01783, 0.01272, 0.01103, 0.01568, 0.0163, 0.01348, 0.01324, 0.01439, 0.01277, 0.01153, 0.00845, 0.00729, 0.00468, 0.00681, 0.00433, 0.04516, 0.41843, 0.36747, 0.24898, 0.19497, 0.16482, 0.35707, 0.34045, 0.22721, 0.20979, 0.07462, 0.23489, 0.18985, 0.09992, 0.06107, 0.25919, 0.36597, 0.40164, 0.354, 0.29839, 0.28776, 0.34263, 0.17409, 0.2238, 0.3641, 0.26571, 0.20944, 0.29786, 0.30905, 0.145, 0.10618, 0.20764, 0.27868, 0.29502, 0.14186, 0.14425, 0.12665, 0.35699, 0.41905, 0.30525, 0.1367, 0.13071, 0.22843, 0.21895, 0.15962, 0.12253, 0.07815, 0.07116, 0.06029, 0.03952, 0.10733, 0.19466, 0.17432, 0.12564, 0.07599, 0.02543, 0.03877, 0.06637, 0.06971, 0.07075, 0.02604, 0.04605, 0.01736, 0.01743, 0.02347, 0.01642, 0.01262, 0.00633, 0.19125, 0.49413, 0.43406, 0.32534, 0.40838, 0.38124, 0.2896, 0.11445, 0.06051, 0.05696, 0.06598, 0.25973, 0.2736, 0.22352, 0.21977, 0.15814, 0.14106, 0.13058, 0.13974, 0.09572, 0.10101, 0.08897, 0.07826, 0.01469, 0.0294, 0.20331, 0.21437, 0.20694, 0.26328, 0.30575, 0.25659, 0.18087, 0.04241, 0.09197, 0.12284, 0.06338, 0.02027, 0.009, 0.00538, 0.20228, 0.28416, 0.20209, 0.0943, 0.01866, 0.08186, 0.11056, 0.07525, 0.04093, 0.07424, 0.11566, 0.2263, 0.17981, 0.14852, 0.1047, 0.11669, 0.28313, 0.34353, 0.28018, 0.1364, 0.09847, 0.1403, 0.10629, 0.05286, 0.03399, 0.00977, 0.05067, 0.03576, 0.13645, 0.13684, 0.09655, 0.05463, 0.10642, 0.23017, 0.20574, 0.15641, 0.10488, 0.06413, 0.04419, 0.04598, 0.01937, 0.0057 ], "comparison": { "original": "Third, we see the bible as a living text where the holy spirit speaks to us today.", "retranscribed": "Third, we see the Bible as a living text where the Holy Spirit speaks to us today.", "reference_tokens": [ "third", "we", "see", "the", "bible", "as", "a", "living", "text", "where", "the", "holy", "spirit", "speaks", "to", "us", "today" ], "hypothesis_tokens": [ "third", "we", "see", "the", "bible", "as", "a", "living", "text", "where", "the", "holy", "spirit", "speaks", "to", "us", "today" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 17, "reference_words": 17, "hypothesis_words": 17, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "third", "hypothesis": "third", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "we", "hypothesis": "we", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "see", "hypothesis": "see", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "bible", "hypothesis": "bible", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "as", "hypothesis": "as", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "living", "hypothesis": "living", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "text", "hypothesis": "text", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "where", "hypothesis": "where", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "holy", "hypothesis": "holy", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "spirit", "hypothesis": "spirit", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "speaks", "hypothesis": "speaks", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "us", "hypothesis": "us", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "today", "hypothesis": "today", "reference_index": 16, "hypothesis_index": 16 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.49413, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Neutral", "emotion_confidence": 0.7896141409873962, "duration_seconds": 16.177999999999997, "mos": 3.3081, "audio_variant": "original", "original_transcript_raw": "Up until march twenty sixth, I led the nhs england team that built the federated data platform. I'm speaking up now because I feel the debate has become detached from technical reality. Working with palantir was a very positive experience. They were high calibre individuals. ", "original_transcript": "Up until march twenty sixth, I led the nhs england team that built the federated data platform. I'm speaking up now because I feel the debate has become detached from technical reality. Working with palantir was a very positive experience. They were high calibre individuals.", "retranscribed_transcript": "Up until March twenty-six, I led the NHS England team that built the federated data platform. I'm speaking up now because I feel the debate has become detached from technical reality. Working with Palantir was a very positive experience. They were high-caliber individuals.", "backend": "qwen", "emotion_analyzed_seconds": 16.178, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-048", "energy": { "value": 0.455078125, "bucket": "low" }, "audio_url": "audio/utterance-048.wav", "spectrogram_url": "spectrograms/utterance-048.png", "waveform": [ 0.45259, 1.18916, 0.66782, 0.70735, 0.82605, 0.58546, 0.93076, 0.47016, 0.41233, 0.72137, 0.96823, 0.5064, 0.71223, 0.56887, 0.14861, 0.42446, 0.51838, 0.56773, 0.93264, 0.72644, 0.50235, 0.02324, 0.12329, 0.60026, 0.40423, 0.36511, 0.18327, 0.02851, 0.00783, 0.78376, 0.5078, 0.43927, 0.37523, 0.8127, 0.55878, 0.64848, 0.50592, 0.49245, 0.79046, 0.4881, 0.49498, 0.08881, 0.72456, 0.15664, 0.63532, 0.24526, 0.0254, 0.00998, 0.24278, 0.10671, 0.99119, 0.43088, 0.41116, 0.30218, 0.72878, 0.36751, 0.18618, 0.39639, 1.06929, 0.0501, 0.58487, 0.59028, 0.32197, 0.02673, 1.20998, 0.94776, 0.49495, 1.2545, 0.60432, 1.19479, 0.69526, 0.59654, 0.86709, 0.84176, 0.61029, 0.09596, 0.02736, 0.00354, 0.33924, 0.17786, 0.79125, 0.44566, 0.38657, 0.76466, 0.47982, 0.07115, 0.06765, 0.41509, 0.09805, 0.64284, 0.48342, 0.68387, 0.01444, 0.3424, 0.35374, 1.15296, 0.36879, 0.40849, 0.25161, 0.45744, 0.16296, 0.4982, 0.37404, 0.34882, 0.90989, 0.29486, 0.29828, 0.55682, 0.97828, 0.39718, 0.2979, 0.5492, 0.70829, 0.51859, 0.42162, 0.4519, 0.38284, 0.50139, 0.44788, 0.05299, 0.00415, 0.38487, 0.99768, 0.16829, 0.86444, 0.32908, 1.19003, 0.73526, 0.59922, 0.7501, 0.65835, 0.36276, 0.62203, 0.60916, 0.30354, 0.2828, 0.02521, 0.32422, 1.17022, 0.97314, 0.67469, 0.01747, 0.74789, 1.22106, 0.40532, 1.01152, 0.61072, 0.35947, 0.60853, 1.22917, 0.7457, 0.48032, 0.27755, 0.43527, 0.38863, 0.19359, 0.00923, 0.16057, 0.9267, 0.8644, 0.53811, 0.61974, 0.66688, 0.24325, 0.01213, 0.06724, 0.16145, 1.07424, 0.62064, 0.00999, 1.00329, 0.69997, 0.58267, 0.64578, 0.67771, 0.79066, 0.36413, 0.58469, 0.54395, 0.099 ], "comparison": { "original": "Up until march twenty sixth, I led the nhs england team that built the federated data platform. I'm speaking up now because I feel the debate has become detached from technical reality. Working with palantir was a very positive experience. They were high calibre individuals.", "retranscribed": "Up until March twenty-six, I led the NHS England team that built the federated data platform. I'm speaking up now because I feel the debate has become detached from technical reality. Working with Palantir was a very positive experience. They were high-caliber individuals.", "reference_tokens": [ "up", "until", "march", "twenty", "sixth", "i", "led", "the", "nhs", "england", "team", "that", "built", "the", "federated", "data", "platform", "im", "speaking", "up", "now", "because", "i", "feel", "the", "debate", "has", "become", "detached", "from", "technical", "reality", "working", "with", "palantir", "was", "a", "very", "positive", "experience", "they", "were", "high", "calibre", "individuals" ], "hypothesis_tokens": [ "up", "until", "march", "twenty", "six", "i", "led", "the", "nhs", "england", "team", "that", "built", "the", "federated", "data", "platform", "im", "speaking", "up", "now", "because", "i", "feel", "the", "debate", "has", "become", "detached", "from", "technical", "reality", "working", "with", "palantir", "was", "a", "very", "positive", "experience", "they", "were", "high", "caliber", "individuals" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 43, "reference_words": 45, "hypothesis_words": 45, "edits": 2 }, "wer": 0.044444444444444446, "wer_percent": 4.444444444444445, "alignment": [ { "op": "equal", "reference": "up", "hypothesis": "up", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "until", "hypothesis": "until", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "march", "hypothesis": "march", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "twenty", "hypothesis": "twenty", "reference_index": 3, "hypothesis_index": 3 }, { "op": "substitute", "reference": "sixth", "hypothesis": "six", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "led", "hypothesis": "led", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "nhs", "hypothesis": "nhs", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "england", "hypothesis": "england", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "team", "hypothesis": "team", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "built", "hypothesis": "built", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "federated", "hypothesis": "federated", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "data", "hypothesis": "data", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "platform", "hypothesis": "platform", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "im", "hypothesis": "im", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "speaking", "hypothesis": "speaking", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "up", "hypothesis": "up", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "now", "hypothesis": "now", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "because", "hypothesis": "because", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "feel", "hypothesis": "feel", "reference_index": 23, "hypothesis_index": 23 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 24, "hypothesis_index": 24 }, { "op": "equal", "reference": "debate", "hypothesis": "debate", "reference_index": 25, "hypothesis_index": 25 }, { "op": "equal", "reference": "has", "hypothesis": "has", "reference_index": 26, "hypothesis_index": 26 }, { "op": "equal", "reference": "become", "hypothesis": "become", "reference_index": 27, "hypothesis_index": 27 }, { "op": "equal", "reference": "detached", "hypothesis": "detached", "reference_index": 28, "hypothesis_index": 28 }, { "op": "equal", "reference": "from", "hypothesis": "from", "reference_index": 29, "hypothesis_index": 29 }, { "op": "equal", "reference": "technical", "hypothesis": "technical", "reference_index": 30, "hypothesis_index": 30 }, { "op": "equal", "reference": "reality", "hypothesis": "reality", "reference_index": 31, "hypothesis_index": 31 }, { "op": "equal", "reference": "working", "hypothesis": "working", "reference_index": 32, "hypothesis_index": 32 }, { "op": "equal", "reference": "with", "hypothesis": "with", "reference_index": 33, "hypothesis_index": 33 }, { "op": "equal", "reference": "palantir", "hypothesis": "palantir", "reference_index": 34, "hypothesis_index": 34 }, { "op": "equal", "reference": "was", "hypothesis": "was", "reference_index": 35, "hypothesis_index": 35 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 36, "hypothesis_index": 36 }, { "op": "equal", "reference": "very", "hypothesis": "very", "reference_index": 37, "hypothesis_index": 37 }, { "op": "equal", "reference": "positive", "hypothesis": "positive", "reference_index": 38, "hypothesis_index": 38 }, { "op": "equal", "reference": "experience", "hypothesis": "experience", "reference_index": 39, "hypothesis_index": 39 }, { "op": "equal", "reference": "they", "hypothesis": "they", "reference_index": 40, "hypothesis_index": 40 }, { "op": "equal", "reference": "were", "hypothesis": "were", "reference_index": 41, "hypothesis_index": 41 }, { "op": "equal", "reference": "high", "hypothesis": "high", "reference_index": 42, "hypothesis_index": 42 }, { "op": "substitute", "reference": "calibre", "hypothesis": "caliber", "reference_index": 43, "hypothesis_index": 43 }, { "op": "equal", "reference": "individuals", "hypothesis": "individuals", "reference_index": 44, "hypothesis_index": 44 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz float32 WAV", "source_peak_abs": 1.2545, "audio_sample_format": "float32" }, { "language": "English", "emotion": "Neutral", "emotion_confidence": 0.49494925141334534, "duration_seconds": 2.338000000000001, "mos": 3.0816, "audio_variant": "original", "original_transcript_raw": "Fascinating. What part of italy? ", "original_transcript": "Fascinating. What part of italy?", "retranscribed_transcript": "Fascinating. What part of Italy?", "backend": "qwen", "emotion_analyzed_seconds": 2.338, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-049", "energy": { "value": 0.55078125, "bucket": "medium" }, "audio_url": "audio/utterance-049.wav", "spectrogram_url": "spectrograms/utterance-049.png", "waveform": [ 0.04237, 0.32874, 0.32749, 0.29152, 0.26212, 0.23739, 0.24949, 0.15539, 0.11998, 0.05497, 0.08201, 0.06987, 0.08288, 0.08779, 0.09383, 0.08532, 0.0703, 0.37434, 0.36829, 0.27582, 0.31011, 0.36356, 0.38732, 0.27922, 0.33336, 0.28929, 0.3439, 0.24745, 0.33072, 0.23171, 0.13556, 0.10336, 0.05503, 0.05568, 0.05996, 0.11791, 0.28085, 0.32247, 0.30498, 0.21086, 0.1962, 0.14309, 0.08609, 0.0917, 0.07309, 0.04441, 0.01866, 0.0197, 0.02573, 0.01611, 0.02887, 0.02551, 0.01215, 0.00603, 0.00356, 0.00409, 0.0049, 0.00302, 0.00331, 0.00369, 0.00453, 0.00438, 0.00535, 0.00608, 0.01889, 0.02615, 0.03837, 0.04509, 0.04295, 0.03989, 0.05065, 0.04707, 0.04301, 0.03946, 0.03052, 0.02442, 0.01898, 0.01684, 0.01423, 0.01644, 0.01305, 0.00993, 0.00954, 0.00907, 0.01457, 0.01203, 0.00958, 0.01133, 0.01279, 0.01036, 0.01009, 0.01017, 0.00946, 0.01038, 0.00759, 0.00756, 0.00704, 0.00702, 0.02082, 0.0374, 0.06021, 0.23464, 0.33611, 0.32337, 0.3347, 0.3312, 0.27613, 0.11363, 0.09197, 0.06505, 0.04377, 0.04162, 0.0287, 0.01934, 0.01895, 0.02174, 0.04948, 0.52395, 0.59317, 0.5621, 0.46618, 0.44804, 0.45913, 0.32595, 0.35783, 0.36411, 0.2759, 0.19801, 0.08051, 0.08627, 0.08677, 0.02491, 0.0418, 0.03876, 0.09676, 0.23381, 0.09739, 0.06852, 0.05668, 0.06537, 0.15965, 0.27796, 0.23048, 0.14545, 0.13333, 0.10007, 0.0747, 0.03532, 0.04925, 0.03883, 0.02907, 0.12483, 0.16185, 0.12686, 0.11325, 0.08119, 0.10492, 0.13132, 0.13039, 0.1217, 0.12441, 0.08815, 0.09118, 0.08324, 0.0603, 0.03103, 0.00895, 0.00858, 0.00724, 0.00447, 0.00423, 0.00423, 0.00259, 0.00298, 0.00232, 0.00241, 0.00235, 0.00166, 0.00178, 0.00161 ], "comparison": { "original": "Fascinating. What part of italy?", "retranscribed": "Fascinating. What part of Italy?", "reference_tokens": [ "fascinating", "what", "part", "of", "italy" ], "hypothesis_tokens": [ "fascinating", "what", "part", "of", "italy" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "fascinating", "hypothesis": "fascinating", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "what", "hypothesis": "what", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "part", "hypothesis": "part", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "italy", "hypothesis": "italy", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.59317, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Neutral", "emotion_confidence": 0.533680260181427, "duration_seconds": 3.651999999999987, "mos": 3.5972, "audio_variant": "cleaned", "original_transcript_raw": "i meet extraordinary and interesting characters oyal", "original_transcript": "i meet extraordinary and interesting characters oyal", "retranscribed_transcript": "I meet extraordinary and interesting characters. So yeah.", "backend": "qwen", "emotion_analyzed_seconds": 3.652, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-050", "energy": { "value": 0.5390625, "bucket": "medium" }, "audio_url": "audio/utterance-050.wav", "spectrogram_url": "spectrograms/utterance-050.png", "waveform": [ 0.01562, 0.10329, 0.10232, 0.13942, 0.16951, 0.17824, 0.23214, 0.34128, 0.33821, 0.40936, 0.39566, 0.40726, 0.63483, 0.76967, 0.8417, 0.71352, 0.41528, 0.38511, 0.4061, 0.51247, 0.46837, 0.40857, 0.42205, 0.08589, 0.03748, 0.03451, 0.04992, 0.03974, 0.02142, 0.00937, 0.01368, 0.02239, 0.19238, 0.19589, 0.04975, 0.00553, 0.07197, 0.12543, 0.12807, 0.13726, 0.12799, 0.14555, 0.13277, 0.03876, 0.06376, 0.08219, 0.07365, 0.18312, 0.24385, 0.27853, 0.33152, 0.38272, 0.15466, 0.13559, 0.10098, 0.26368, 0.3499, 0.27907, 0.30652, 0.30723, 0.28038, 0.29823, 0.2582, 0.26738, 0.30671, 0.24743, 0.27064, 0.19801, 0.14615, 0.15411, 0.1618, 0.14197, 0.20103, 0.19359, 0.14583, 0.14402, 0.1492, 0.16563, 0.15896, 0.17918, 0.18815, 0.13384, 0.07174, 0.1142, 0.22912, 0.2108, 0.23011, 0.21961, 0.24202, 0.26673, 0.15893, 0.04891, 0.13371, 0.11587, 0.09427, 0.0904, 0.10869, 0.09347, 0.1038, 0.09852, 0.11386, 0.0723, 0.15237, 0.10424, 0.11361, 0.13002, 0.10349, 0.00589, 0.02265, 0.06554, 0.04378, 0.15043, 0.12699, 0.16404, 0.18298, 0.06726, 0.02209, 0.23503, 0.05389, 0.43955, 0.25948, 0.14442, 0.13869, 0.16198, 0.11456, 0.11094, 0.1109, 0.09679, 0.11075, 0.13241, 0.09628, 0.04936, 0.01729, 0.00484, 0.00225, 0.00165, 0.10892, 0.08956, 0.13952, 0.21088, 0.09842, 0.04403, 0.0289, 0.03015, 0.02485, 0.02785, 0.06192, 0.09342, 0.14514, 0.1478, 0.06668, 0.03191, 0.07106, 0.05148, 0.04846, 0.05747, 0.05557, 0.0575, 0.07198, 0.08588, 0.06768, 0.06168, 0.08062, 0.09742, 0.11106, 0.08493, 0.08678, 0.06168, 0.06035, 0.07212, 0.03077, 0.0303, 0.01675, 0.00827, 0.0045, 0.0049, 0.00485, 0.00611, 0.00627, 0.00761 ], "comparison": { "original": "i meet extraordinary and interesting characters oyal", "retranscribed": "I meet extraordinary and interesting characters. So yeah.", "reference_tokens": [ "i", "meet", "extraordinary", "and", "interesting", "characters", "oyal" ], "hypothesis_tokens": [ "i", "meet", "extraordinary", "and", "interesting", "characters", "so", "yeah" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 1, "hits": 6, "reference_words": 7, "hypothesis_words": 8, "edits": 2 }, "wer": 0.2857142857142857, "wer_percent": 28.57142857142857, "alignment": [ { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "meet", "hypothesis": "meet", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "extraordinary", "hypothesis": "extraordinary", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "interesting", "hypothesis": "interesting", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "characters", "hypothesis": "characters", "reference_index": 5, "hypothesis_index": 5 }, { "op": "insert", "reference": null, "hypothesis": "so", "reference_index": null, "hypothesis_index": 6 }, { "op": "substitute", "reference": "oyal", "hypothesis": "yeah", "reference_index": 6, "hypothesis_index": 7 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.8417, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Neutral", "emotion_confidence": 0.6410962343215942, "duration_seconds": 17.65299999999999, "mos": 4.0366, "audio_variant": "cleaned", "original_transcript_raw": "The maternity leave and all that stuff. So I took out a quick little six rand loan so I could be secure after we moved into our apartment and just have the millennia to help her. And then I just, what I started doing is I just started racking up personal loans because I was stupid with my money and would. ", "original_transcript": "The maternity leave and all that stuff. So I took out a quick little six rand loan so I could be secure after we moved into our apartment and just have the millennia to help her. And then I just, what I started doing is I just started racking up personal loans because I was stupid with my money and would.", "retranscribed_transcript": "The maternity leave and all that stuff. So I took out a quick little six grand loan so I could be secure after we moved into our apartment and just have the millennial to help her. And then I just what I started doing is I just started racking up personal loans because I was stupid with my money, and would.", "backend": "qwen", "emotion_analyzed_seconds": 17.653, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-051", "energy": { "value": 0.54296875, "bucket": "medium" }, "audio_url": "audio/utterance-051.wav", "spectrogram_url": "spectrograms/utterance-051.png", "waveform": [ 0.33034, 0.28073, 0.23281, 0.21825, 0.16033, 0.1421, 0.12215, 0.14858, 0.24662, 0.17811, 0.13038, 0.15433, 0.16178, 0.17392, 0.17156, 0.12671, 0.16004, 0.15612, 0.22224, 0.0689, 0.17608, 0.21374, 0.20281, 0.10279, 0.17095, 0.13553, 0.24429, 0.08088, 0.11258, 0.25665, 0.2199, 0.05326, 0.07919, 0.22251, 0.13011, 0.14287, 0.1447, 0.14483, 0.08833, 0.05643, 0.20891, 0.08533, 0.1571, 0.17218, 0.18599, 0.20408, 0.23244, 0.19697, 0.06614, 0.00432, 0.01821, 0.23758, 0.39378, 0.15467, 0.09952, 0.16466, 0.09105, 0.07255, 0.21717, 0.18348, 0.21979, 0.14444, 0.16508, 0.22055, 0.15969, 0.15339, 0.17884, 0.1432, 0.16835, 0.18564, 0.07038, 0.18914, 0.14106, 0.16518, 0.15995, 0.15024, 0.11043, 0.05373, 0.24705, 0.26225, 0.03993, 0.00095, 3e-05, 2e-05, 0.06494, 0.16837, 0.1983, 0.16602, 0.08952, 0.2184, 0.14638, 0.0115, 0.00087, 0.00064, 0.15691, 0.28111, 0.11262, 0.31167, 0.18807, 0.00705, 5e-05, 2e-05, 0.00026, 0.00079, 0.0023, 0.00263, 8e-05, 4e-05, 0.43525, 0.35228, 0.16325, 0.24727, 0.23478, 0.28208, 0.30892, 0.18067, 0.21571, 0.09925, 0.00232, 2e-05, 2e-05, 0.00124, 0.20865, 0.24466, 0.26731, 0.08158, 0.33207, 0.25548, 0.11098, 0.21256, 0.22814, 0.21719, 0.17965, 0.08576, 0.28722, 0.22558, 0.10018, 0.21093, 0.21706, 0.13627, 0.14512, 0.08077, 0.15844, 0.12713, 0.1167, 0.14006, 0.13671, 0.16667, 0.08461, 0.11593, 0.14926, 0.20907, 0.21818, 0.05495, 0.04909, 0.1392, 0.14205, 0.10574, 0.11622, 0.14902, 0.1858, 0.14754, 0.14919, 0.14844, 0.00038, 0.00901, 0.01484, 0.0115, 0.00932, 0.20116, 0.19107, 0.1916, 0.09174, 0.12523, 0.1042, 0.03051, 0.01955, 0.00311, 0.02951, 0.01251 ], "comparison": { "original": "The maternity leave and all that stuff. So I took out a quick little six rand loan so I could be secure after we moved into our apartment and just have the millennia to help her. And then I just, what I started doing is I just started racking up personal loans because I was stupid with my money and would.", "retranscribed": "The maternity leave and all that stuff. So I took out a quick little six grand loan so I could be secure after we moved into our apartment and just have the millennial to help her. And then I just what I started doing is I just started racking up personal loans because I was stupid with my money, and would.", "reference_tokens": [ "the", "maternity", "leave", "and", "all", "that", "stuff", "so", "i", "took", "out", "a", "quick", "little", "six", "rand", "loan", "so", "i", "could", "be", "secure", "after", "we", "moved", "into", "our", "apartment", "and", "just", "have", "the", "millennia", "to", "help", "her", "and", "then", "i", "just", "what", "i", "started", "doing", "is", "i", "just", "started", "racking", "up", "personal", "loans", "because", "i", "was", "stupid", "with", "my", "money", "and", "would" ], "hypothesis_tokens": [ "the", "maternity", "leave", "and", "all", "that", "stuff", "so", "i", "took", "out", "a", "quick", "little", "six", "grand", "loan", "so", "i", "could", "be", "secure", "after", "we", "moved", "into", "our", "apartment", "and", "just", "have", "the", "millennial", "to", "help", "her", "and", "then", "i", "just", "what", "i", "started", "doing", "is", "i", "just", "started", "racking", "up", "personal", "loans", "because", "i", "was", "stupid", "with", "my", "money", "and", "would" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 59, "reference_words": 61, "hypothesis_words": 61, "edits": 2 }, "wer": 0.03278688524590164, "wer_percent": 3.278688524590164, "alignment": [ { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "maternity", "hypothesis": "maternity", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "leave", "hypothesis": "leave", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "all", "hypothesis": "all", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "stuff", "hypothesis": "stuff", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "so", "hypothesis": "so", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "took", "hypothesis": "took", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "out", "hypothesis": "out", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "quick", "hypothesis": "quick", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "little", "hypothesis": "little", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "six", "hypothesis": "six", "reference_index": 14, "hypothesis_index": 14 }, { "op": "substitute", "reference": "rand", "hypothesis": "grand", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "loan", "hypothesis": "loan", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "so", "hypothesis": "so", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "could", "hypothesis": "could", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "be", "hypothesis": "be", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "secure", "hypothesis": "secure", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "after", "hypothesis": "after", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "we", "hypothesis": "we", "reference_index": 23, "hypothesis_index": 23 }, { "op": "equal", "reference": "moved", "hypothesis": "moved", "reference_index": 24, "hypothesis_index": 24 }, { "op": "equal", "reference": "into", "hypothesis": "into", "reference_index": 25, "hypothesis_index": 25 }, { "op": "equal", "reference": "our", "hypothesis": "our", "reference_index": 26, "hypothesis_index": 26 }, { "op": "equal", "reference": "apartment", "hypothesis": "apartment", "reference_index": 27, "hypothesis_index": 27 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 28, "hypothesis_index": 28 }, { "op": "equal", "reference": "just", "hypothesis": "just", "reference_index": 29, "hypothesis_index": 29 }, { "op": "equal", "reference": "have", "hypothesis": "have", "reference_index": 30, "hypothesis_index": 30 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 31, "hypothesis_index": 31 }, { "op": "substitute", "reference": "millennia", "hypothesis": "millennial", "reference_index": 32, "hypothesis_index": 32 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 33, "hypothesis_index": 33 }, { "op": "equal", "reference": "help", "hypothesis": "help", "reference_index": 34, "hypothesis_index": 34 }, { "op": "equal", "reference": "her", "hypothesis": "her", "reference_index": 35, "hypothesis_index": 35 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 36, "hypothesis_index": 36 }, { "op": "equal", "reference": "then", "hypothesis": "then", "reference_index": 37, "hypothesis_index": 37 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 38, "hypothesis_index": 38 }, { "op": "equal", "reference": "just", "hypothesis": "just", "reference_index": 39, "hypothesis_index": 39 }, { "op": "equal", "reference": "what", "hypothesis": "what", "reference_index": 40, "hypothesis_index": 40 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 41, "hypothesis_index": 41 }, { "op": "equal", "reference": "started", "hypothesis": "started", "reference_index": 42, "hypothesis_index": 42 }, { "op": "equal", "reference": "doing", "hypothesis": "doing", "reference_index": 43, "hypothesis_index": 43 }, { "op": "equal", "reference": "is", "hypothesis": "is", "reference_index": 44, "hypothesis_index": 44 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 45, "hypothesis_index": 45 }, { "op": "equal", "reference": "just", "hypothesis": "just", "reference_index": 46, "hypothesis_index": 46 }, { "op": "equal", "reference": "started", "hypothesis": "started", "reference_index": 47, "hypothesis_index": 47 }, { "op": "equal", "reference": "racking", "hypothesis": "racking", "reference_index": 48, "hypothesis_index": 48 }, { "op": "equal", "reference": "up", "hypothesis": "up", "reference_index": 49, "hypothesis_index": 49 }, { "op": "equal", "reference": "personal", "hypothesis": "personal", "reference_index": 50, "hypothesis_index": 50 }, { "op": "equal", "reference": "loans", "hypothesis": "loans", "reference_index": 51, "hypothesis_index": 51 }, { "op": "equal", "reference": "because", "hypothesis": "because", "reference_index": 52, "hypothesis_index": 52 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 53, "hypothesis_index": 53 }, { "op": "equal", "reference": "was", "hypothesis": "was", "reference_index": 54, "hypothesis_index": 54 }, { "op": "equal", "reference": "stupid", "hypothesis": "stupid", "reference_index": 55, "hypothesis_index": 55 }, { "op": "equal", "reference": "with", "hypothesis": "with", "reference_index": 56, "hypothesis_index": 56 }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 57, "hypothesis_index": 57 }, { "op": "equal", "reference": "money", "hypothesis": "money", "reference_index": 58, "hypothesis_index": 58 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 59, "hypothesis_index": 59 }, { "op": "equal", "reference": "would", "hypothesis": "would", "reference_index": 60, "hypothesis_index": 60 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.43525, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Neutral", "emotion_confidence": 0.7673678398132324, "duration_seconds": 15.325000000000045, "mos": 3.6438, "audio_variant": "original", "original_transcript_raw": "Tara checks her husband's cell phone wallet pants pockets dog walking route, and just anywhere that he might be going now andrew says she drills down on him for hours at a time if he even mentions another woman in passing. ", "original_transcript": "Tara checks her husband's cell phone wallet pants pockets dog walking route, and just anywhere that he might be going now andrew says she drills down on him for hours at a time if he even mentions another woman in passing.", "retranscribed_transcript": "Alright, Tara checks her husband's cell phone, wallet, pants pockets, dog walking route, and just anywhere that he might be going. Now Andrew says she drills down on him for hours at a time if he even mentions another woman in passing.", "backend": "qwen", "emotion_analyzed_seconds": 15.325, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-052", "energy": { "value": 0.58984375, "bucket": "high" }, "audio_url": "audio/utterance-052.wav", "spectrogram_url": "spectrograms/utterance-052.png", "waveform": [ 0.32785, 0.32281, 0.07874, 0.10456, 0.41149, 0.41196, 0.4086, 0.29605, 0.15404, 0.38927, 0.32721, 0.24668, 0.09495, 0.19702, 0.28089, 0.30061, 0.33398, 0.17513, 0.20441, 0.17797, 0.09718, 0.1245, 0.34741, 0.28693, 0.17544, 0.16794, 0.15355, 0.11762, 0.07426, 0.06451, 0.24475, 0.24837, 0.19596, 0.16529, 0.06827, 0.00448, 0.11284, 0.20458, 0.16134, 0.0372, 0.01648, 0.27511, 0.25263, 0.14, 0.11233, 0.06242, 0.04318, 0.16855, 0.37486, 0.29107, 0.22404, 0.03775, 0.32344, 0.33836, 0.27495, 0.0961, 0.07379, 0.15974, 0.257, 0.29996, 0.37648, 0.16442, 0.14033, 0.17063, 0.2065, 0.18936, 0.02138, 0.15992, 0.16939, 0.15616, 0.12791, 0.17763, 0.22522, 0.21851, 0.16496, 0.06752, 0.10701, 0.07581, 0.20429, 0.24245, 0.0548, 0.11624, 0.09746, 0.18637, 0.11253, 0.03689, 0.00775, 0.00661, 0.00395, 0.00398, 0.00564, 0.00438, 0.00372, 0.30671, 0.13369, 0.35887, 0.3768, 0.25639, 0.35079, 0.1039, 0.30198, 0.30818, 0.33094, 0.19739, 0.243, 0.22446, 0.11842, 0.23446, 0.36116, 0.26969, 0.1191, 0.28907, 0.31543, 0.20259, 0.21983, 0.21815, 0.11687, 0.15513, 0.13834, 0.07449, 0.01461, 0.16073, 0.29524, 0.20536, 0.01128, 0.20673, 0.28666, 0.22063, 0.18478, 0.11366, 0.13844, 0.06823, 0.18562, 0.15463, 0.03921, 0.26602, 0.22279, 0.24474, 0.27287, 0.17112, 0.01348, 0.01017, 0.00476, 0.00261, 0.19806, 0.01957, 0.10353, 0.1044, 0.08018, 0.08805, 0.08434, 0.06413, 0.05449, 0.05216, 0.17426, 0.28637, 0.09193, 0.18975, 0.27056, 0.16096, 0.04755, 0.20452, 0.17131, 0.241, 0.18226, 0.15535, 0.20257, 0.21667, 0.17596, 0.08075, 0.11147, 0.16673, 0.07572, 0.01336, 0.16534, 0.24615, 0.234, 0.0909, 0.08269, 0.00746 ], "comparison": { "original": "Tara checks her husband's cell phone wallet pants pockets dog walking route, and just anywhere that he might be going now andrew says she drills down on him for hours at a time if he even mentions another woman in passing.", "retranscribed": "Alright, Tara checks her husband's cell phone, wallet, pants pockets, dog walking route, and just anywhere that he might be going. Now Andrew says she drills down on him for hours at a time if he even mentions another woman in passing.", "reference_tokens": [ "tara", "checks", "her", "husbands", "cell", "phone", "wallet", "pants", "pockets", "dog", "walking", "route", "and", "just", "anywhere", "that", "he", "might", "be", "going", "now", "andrew", "says", "she", "drills", "down", "on", "him", "for", "hours", "at", "a", "time", "if", "he", "even", "mentions", "another", "woman", "in", "passing" ], "hypothesis_tokens": [ "alright", "tara", "checks", "her", "husbands", "cell", "phone", "wallet", "pants", "pockets", "dog", "walking", "route", "and", "just", "anywhere", "that", "he", "might", "be", "going", "now", "andrew", "says", "she", "drills", "down", "on", "him", "for", "hours", "at", "a", "time", "if", "he", "even", "mentions", "another", "woman", "in", "passing" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 41, "reference_words": 41, "hypothesis_words": 42, "edits": 1 }, "wer": 0.024390243902439025, "wer_percent": 2.4390243902439024, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "alright", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "tara", "hypothesis": "tara", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "checks", "hypothesis": "checks", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "her", "hypothesis": "her", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "husbands", "hypothesis": "husbands", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "cell", "hypothesis": "cell", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "phone", "hypothesis": "phone", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "wallet", "hypothesis": "wallet", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "pants", "hypothesis": "pants", "reference_index": 7, "hypothesis_index": 8 }, { "op": "equal", "reference": "pockets", "hypothesis": "pockets", "reference_index": 8, "hypothesis_index": 9 }, { "op": "equal", "reference": "dog", "hypothesis": "dog", "reference_index": 9, "hypothesis_index": 10 }, { "op": "equal", "reference": "walking", "hypothesis": "walking", "reference_index": 10, "hypothesis_index": 11 }, { "op": "equal", "reference": "route", "hypothesis": "route", "reference_index": 11, "hypothesis_index": 12 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 12, "hypothesis_index": 13 }, { "op": "equal", "reference": "just", "hypothesis": "just", "reference_index": 13, "hypothesis_index": 14 }, { "op": "equal", "reference": "anywhere", "hypothesis": "anywhere", "reference_index": 14, "hypothesis_index": 15 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 15, "hypothesis_index": 16 }, { "op": "equal", "reference": "he", "hypothesis": "he", "reference_index": 16, "hypothesis_index": 17 }, { "op": "equal", "reference": "might", "hypothesis": "might", "reference_index": 17, "hypothesis_index": 18 }, { "op": "equal", "reference": "be", "hypothesis": "be", "reference_index": 18, "hypothesis_index": 19 }, { "op": "equal", "reference": "going", "hypothesis": "going", "reference_index": 19, "hypothesis_index": 20 }, { "op": "equal", "reference": "now", "hypothesis": "now", "reference_index": 20, "hypothesis_index": 21 }, { "op": "equal", "reference": "andrew", "hypothesis": "andrew", "reference_index": 21, "hypothesis_index": 22 }, { "op": "equal", "reference": "says", "hypothesis": "says", "reference_index": 22, "hypothesis_index": 23 }, { "op": "equal", "reference": "she", "hypothesis": "she", "reference_index": 23, "hypothesis_index": 24 }, { "op": "equal", "reference": "drills", "hypothesis": "drills", "reference_index": 24, "hypothesis_index": 25 }, { "op": "equal", "reference": "down", "hypothesis": "down", "reference_index": 25, "hypothesis_index": 26 }, { "op": "equal", "reference": "on", "hypothesis": "on", "reference_index": 26, "hypothesis_index": 27 }, { "op": "equal", "reference": "him", "hypothesis": "him", "reference_index": 27, "hypothesis_index": 28 }, { "op": "equal", "reference": "for", "hypothesis": "for", "reference_index": 28, "hypothesis_index": 29 }, { "op": "equal", "reference": "hours", "hypothesis": "hours", "reference_index": 29, "hypothesis_index": 30 }, { "op": "equal", "reference": "at", "hypothesis": "at", "reference_index": 30, "hypothesis_index": 31 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 31, "hypothesis_index": 32 }, { "op": "equal", "reference": "time", "hypothesis": "time", "reference_index": 32, "hypothesis_index": 33 }, { "op": "equal", "reference": "if", "hypothesis": "if", "reference_index": 33, "hypothesis_index": 34 }, { "op": "equal", "reference": "he", "hypothesis": "he", "reference_index": 34, "hypothesis_index": 35 }, { "op": "equal", "reference": "even", "hypothesis": "even", "reference_index": 35, "hypothesis_index": 36 }, { "op": "equal", "reference": "mentions", "hypothesis": "mentions", "reference_index": 36, "hypothesis_index": 37 }, { "op": "equal", "reference": "another", "hypothesis": "another", "reference_index": 37, "hypothesis_index": 38 }, { "op": "equal", "reference": "woman", "hypothesis": "woman", "reference_index": 38, "hypothesis_index": 39 }, { "op": "equal", "reference": "in", "hypothesis": "in", "reference_index": 39, "hypothesis_index": 40 }, { "op": "equal", "reference": "passing", "hypothesis": "passing", "reference_index": 40, "hypothesis_index": 41 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.41196, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Neutral", "emotion_confidence": 0.5959238409996033, "duration_seconds": 17.483000000000004, "mos": 3.6991, "audio_variant": "cleaned", "original_transcript_raw": "It is so quiet that none of my coworkers even know i'm using it. Strengthen and tone your legs, increase your mobility flexibility and balance, plus stimulate healthy circulation. My joints feel better, my knees feel better, my back feels better. It makes me feel stronger. ", "original_transcript": "It is so quiet that none of my coworkers even know i'm using it. Strengthen and tone your legs, increase your mobility flexibility and balance, plus stimulate healthy circulation. My joints feel better, my knees feel better, my back feels better. It makes me feel stronger.", "retranscribed_transcript": "It is so quiet that none of my coworkers even know I'm using it. Strengthen and tone your legs, increase your mobility, flexibility, and balance. Plus, stimulate healthy circulation. My joints feel better, my knees feel better, my back feels better. It makes me feel stronger.", "backend": "qwen", "emotion_analyzed_seconds": 17.483, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-053", "energy": { "value": 0.60546875, "bucket": "high" }, "audio_url": "audio/utterance-053.wav", "spectrogram_url": "spectrograms/utterance-053.png", "waveform": [ 0.21144, 0.17664, 0.14912, 0.19034, 0.06351, 0.02822, 0.30155, 0.24689, 0.04818, 0.20288, 0.4346, 0.37176, 0.26969, 0.17551, 0.0061, 0.07702, 0.39194, 0.15053, 0.12161, 0.31495, 0.33242, 0.25712, 0.22043, 0.20246, 0.1968, 0.2229, 0.22411, 0.14156, 0.16109, 0.16769, 0.19617, 0.22272, 0.27367, 0.1937, 0.06592, 0.16091, 0.14346, 0.17703, 0.24677, 0.2648, 0.05076, 0.13827, 0.53559, 0.51771, 0.1595, 0.50769, 0.46358, 0.20071, 0.09079, 0.64063, 0.47062, 0.39841, 0.47588, 0.56617, 0.52373, 0.46062, 0.24046, 0.10184, 0.05495, 0.38175, 0.20914, 0.40342, 0.42882, 0.16828, 0.38425, 0.46121, 0.41886, 0.48075, 0.42301, 0.48694, 0.25317, 0.04081, 0.58284, 0.4621, 0.47795, 0.51945, 0.44959, 0.46615, 0.39343, 0.35791, 0.38755, 0.5418, 0.44551, 0.42398, 0.50764, 0.0962, 0.09247, 0.28341, 0.56482, 0.49874, 0.42795, 0.07482, 0.1318, 0.13376, 0.41175, 0.25963, 0.44599, 0.51362, 0.19825, 0.14047, 0.60617, 0.47633, 0.48261, 0.23759, 0.53529, 0.46521, 0.42588, 0.50042, 0.47039, 0.2814, 0.42349, 0.30751, 0.1125, 0.25252, 0.38735, 0.42621, 0.06498, 0.14039, 0.45109, 0.45759, 0.41426, 0.10277, 0.1477, 0.52893, 0.48614, 0.33016, 0.45984, 0.47625, 0.49509, 0.48658, 0.43298, 0.17144, 0.20848, 0.29488, 0.18529, 0.12666, 0.26953, 0.39035, 0.28086, 0.12657, 0.47423, 0.43184, 0.14486, 0.53044, 0.53243, 0.49242, 0.47588, 0.35956, 0.02342, 0.01352, 0.32419, 0.60214, 0.10698, 0.54376, 0.41438, 0.37566, 0.20802, 0.10415, 0.35967, 0.42097, 0.34273, 0.43307, 0.53157, 0.52752, 0.12567, 0.16096, 0.44627, 0.49398, 0.33506, 0.4226, 0.47978, 0.45063, 0.21937, 0.16678, 0.46301, 0.49961, 0.5035, 0.33469, 0.302, 0.26295 ], "comparison": { "original": "It is so quiet that none of my coworkers even know i'm using it. Strengthen and tone your legs, increase your mobility flexibility and balance, plus stimulate healthy circulation. My joints feel better, my knees feel better, my back feels better. It makes me feel stronger.", "retranscribed": "It is so quiet that none of my coworkers even know I'm using it. Strengthen and tone your legs, increase your mobility, flexibility, and balance. Plus, stimulate healthy circulation. My joints feel better, my knees feel better, my back feels better. It makes me feel stronger.", "reference_tokens": [ "it", "is", "so", "quiet", "that", "none", "of", "my", "coworkers", "even", "know", "im", "using", "it", "strengthen", "and", "tone", "your", "legs", "increase", "your", "mobility", "flexibility", "and", "balance", "plus", "stimulate", "healthy", "circulation", "my", "joints", "feel", "better", "my", "knees", "feel", "better", "my", "back", "feels", "better", "it", "makes", "me", "feel", "stronger" ], "hypothesis_tokens": [ "it", "is", "so", "quiet", "that", "none", "of", "my", "coworkers", "even", "know", "im", "using", "it", "strengthen", "and", "tone", "your", "legs", "increase", "your", "mobility", "flexibility", "and", "balance", "plus", "stimulate", "healthy", "circulation", "my", "joints", "feel", "better", "my", "knees", "feel", "better", "my", "back", "feels", "better", "it", "makes", "me", "feel", "stronger" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 46, "reference_words": 46, "hypothesis_words": 46, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "it", "hypothesis": "it", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "is", "hypothesis": "is", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "so", "hypothesis": "so", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "quiet", "hypothesis": "quiet", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "none", "hypothesis": "none", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "coworkers", "hypothesis": "coworkers", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "even", "hypothesis": "even", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "know", "hypothesis": "know", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "im", "hypothesis": "im", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "using", "hypothesis": "using", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "it", "hypothesis": "it", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "strengthen", "hypothesis": "strengthen", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "tone", "hypothesis": "tone", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "your", "hypothesis": "your", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "legs", "hypothesis": "legs", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "increase", "hypothesis": "increase", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "your", "hypothesis": "your", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "mobility", "hypothesis": "mobility", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "flexibility", "hypothesis": "flexibility", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 23, "hypothesis_index": 23 }, { "op": "equal", "reference": "balance", "hypothesis": "balance", "reference_index": 24, "hypothesis_index": 24 }, { "op": "equal", "reference": "plus", "hypothesis": "plus", "reference_index": 25, "hypothesis_index": 25 }, { "op": "equal", "reference": "stimulate", "hypothesis": "stimulate", "reference_index": 26, "hypothesis_index": 26 }, { "op": "equal", "reference": "healthy", "hypothesis": "healthy", "reference_index": 27, "hypothesis_index": 27 }, { "op": "equal", "reference": "circulation", "hypothesis": "circulation", "reference_index": 28, "hypothesis_index": 28 }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 29, "hypothesis_index": 29 }, { "op": "equal", "reference": "joints", "hypothesis": "joints", "reference_index": 30, "hypothesis_index": 30 }, { "op": "equal", "reference": "feel", "hypothesis": "feel", "reference_index": 31, "hypothesis_index": 31 }, { "op": "equal", "reference": "better", "hypothesis": "better", "reference_index": 32, "hypothesis_index": 32 }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 33, "hypothesis_index": 33 }, { "op": "equal", "reference": "knees", "hypothesis": "knees", "reference_index": 34, "hypothesis_index": 34 }, { "op": "equal", "reference": "feel", "hypothesis": "feel", "reference_index": 35, "hypothesis_index": 35 }, { "op": "equal", "reference": "better", "hypothesis": "better", "reference_index": 36, "hypothesis_index": 36 }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 37, "hypothesis_index": 37 }, { "op": "equal", "reference": "back", "hypothesis": "back", "reference_index": 38, "hypothesis_index": 38 }, { "op": "equal", "reference": "feels", "hypothesis": "feels", "reference_index": 39, "hypothesis_index": 39 }, { "op": "equal", "reference": "better", "hypothesis": "better", "reference_index": 40, "hypothesis_index": 40 }, { "op": "equal", "reference": "it", "hypothesis": "it", "reference_index": 41, "hypothesis_index": 41 }, { "op": "equal", "reference": "makes", "hypothesis": "makes", "reference_index": 42, "hypothesis_index": 42 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 43, "hypothesis_index": 43 }, { "op": "equal", "reference": "feel", "hypothesis": "feel", "reference_index": 44, "hypothesis_index": 44 }, { "op": "equal", "reference": "stronger", "hypothesis": "stronger", "reference_index": 45, "hypothesis_index": 45 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.64063, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Neutral", "emotion_confidence": 0.2589324414730072, "duration_seconds": 1.7909999999999968, "mos": 3.3296, "audio_variant": "cleaned", "original_transcript_raw": "You and kalyani are no different. ", "original_transcript": "You and kalyani are no different.", "retranscribed_transcript": "You and Kalani are no different.", "backend": "qwen", "emotion_analyzed_seconds": 1.791, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-054", "energy": { "value": 0.59375, "bucket": "high" }, "audio_url": "audio/utterance-054.wav", "spectrogram_url": "spectrograms/utterance-054.png", "waveform": [ 0.14896, 0.15306, 0.16512, 0.18891, 0.2325, 0.23899, 0.31508, 0.32968, 0.39272, 0.58438, 0.64255, 0.65368, 0.57453, 0.57851, 0.53067, 0.42026, 0.4093, 0.41209, 0.54009, 0.61953, 0.629, 0.7211, 0.65193, 0.59992, 0.65756, 0.70605, 0.72981, 0.60141, 0.49488, 0.41772, 0.36444, 0.38037, 0.34594, 0.27682, 0.21772, 0.10322, 0.04212, 0.04656, 0.01874, 0.01112, 0.01431, 0.14691, 0.1624, 0.13595, 0.44891, 0.66064, 0.65706, 0.66372, 0.56423, 0.36271, 0.35733, 0.28264, 0.27969, 0.28233, 0.30198, 0.30213, 0.35561, 0.37822, 0.46689, 0.52607, 0.5313, 0.53799, 0.49536, 0.52088, 0.56624, 0.59854, 0.57867, 0.67145, 0.67752, 0.56631, 0.45351, 0.35953, 0.30277, 0.30081, 0.25202, 0.36205, 0.35856, 0.32017, 0.32714, 0.31234, 0.34849, 0.4187, 0.51577, 0.51852, 0.55453, 0.53268, 0.47709, 0.69631, 0.63571, 0.54808, 0.43979, 0.27212, 0.29724, 0.26598, 0.27629, 0.25233, 0.22982, 0.24823, 0.31786, 0.46609, 0.41402, 0.35657, 0.34513, 0.28507, 0.29801, 0.29668, 0.28115, 0.20348, 0.17856, 0.12182, 0.12187, 0.11268, 0.06798, 0.05189, 0.03945, 0.10161, 0.23144, 0.24213, 0.22883, 0.18523, 0.19307, 0.13729, 0.10298, 0.05275, 0.03981, 0.03702, 0.02747, 0.03707, 0.03172, 0.02931, 0.02611, 0.03232, 0.02408, 0.02042, 0.0116, 0.01627, 0.04791, 0.05826, 0.06881, 0.07661, 0.07197, 0.06001, 0.05603, 0.06146, 0.04387, 0.0427, 0.03802, 0.03847, 0.0364, 0.03887, 0.03499, 0.0268, 0.02122, 0.0099, 0.0042, 0.00067, 0.00292, 0.03026, 0.00615, 0.00776, 0.00578, 0.00301, 0.00226, 0.00312, 0.00228, 0.00158, 0.00134, 0.00103, 0.00072, 0.00056, 0.00039, 0.00028, 0.00029, 0.00016, 0.00012, 0.00279, 0.00442, 0.00665, 0.00774, 0.00967 ], "comparison": { "original": "You and kalyani are no different.", "retranscribed": "You and Kalani are no different.", "reference_tokens": [ "you", "and", "kalyani", "are", "no", "different" ], "hypothesis_tokens": [ "you", "and", "kalani", "are", "no", "different" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 6, "hypothesis_words": 6, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "and", "hypothesis": "and", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "kalyani", "hypothesis": "kalani", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "are", "hypothesis": "are", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "different", "hypothesis": "different", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.72981, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Sad", "emotion_confidence": 0.5119355320930481, "duration_seconds": 1.9960000000000022, "mos": 3.1685, "audio_variant": "cleaned", "original_transcript_raw": "That my my sister, I know it. ", "original_transcript": "That my my sister, I know it.", "retranscribed_transcript": "My sister. I know.", "backend": "qwen", "emotion_analyzed_seconds": 1.996, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-055", "energy": { "value": 0.392578125, "bucket": "low" }, "audio_url": "audio/utterance-055.wav", "spectrogram_url": "spectrograms/utterance-055.png", "waveform": [ 0.03885, 0.03753, 0.23459, 0.37675, 0.4263, 0.26922, 0.18969, 0.15535, 0.14399, 0.14632, 0.17374, 0.17474, 0.18386, 0.25643, 0.30849, 0.30787, 0.29123, 0.22444, 0.15255, 0.12079, 0.07428, 0.05741, 0.03516, 0.01736, 0.00908, 0.00764, 0.04729, 0.03879, 0.02589, 0.06903, 0.07416, 0.0728, 0.0998, 0.09714, 0.07637, 0.07707, 0.02329, 0.02367, 0.0134, 0.00795, 0.00375, 0.00361, 0.00444, 0.00272, 0.00318, 0.00149, 0.00376, 0.0027, 0.00331, 0.01616, 0.22886, 0.20598, 0.24829, 0.26977, 0.27355, 0.22638, 0.22121, 0.17529, 0.11508, 0.05703, 0.05437, 0.0402, 0.05665, 0.05306, 0.06042, 0.07144, 0.04992, 0.03661, 0.06797, 0.33055, 0.30218, 0.30554, 0.24203, 0.22576, 0.19414, 0.12366, 0.09008, 0.07606, 0.05429, 0.03183, 0.02535, 0.00842, 0.0052, 0.00566, 0.00796, 0.01242, 0.16349, 0.05614, 0.02508, 0.2634, 0.37917, 0.30505, 0.31735, 0.31039, 0.25564, 0.23375, 0.23537, 0.23301, 0.22553, 0.18058, 0.16635, 0.17011, 0.14636, 0.10759, 0.12832, 0.11466, 0.10052, 0.1025, 0.0996, 0.08822, 0.07616, 0.04747, 0.03012, 0.01586, 0.01227, 0.00568, 0.00489, 0.00292, 0.00298, 0.00133, 0.00155, 0.00123, 0.00165, 0.0018, 0.00116, 0.00165, 0.0027, 0.00192, 0.00678, 0.03265, 0.05014, 0.11838, 0.14291, 0.26376, 0.20498, 0.24866, 0.23475, 0.30214, 0.2143, 0.24829, 0.19178, 0.16933, 0.17633, 0.18518, 0.19234, 0.18473, 0.15496, 0.22801, 0.30305, 0.29579, 0.31475, 0.28132, 0.23129, 0.21949, 0.2424, 0.22482, 0.22514, 0.20262, 0.21317, 0.20195, 0.18947, 0.19369, 0.20346, 0.21448, 0.26166, 0.28393, 0.23797, 0.23617, 0.273, 0.20907, 0.20424, 0.15587, 0.1821, 0.18481, 0.17273, 0.1564, 0.12755, 0.07792, 0.07211, 0.07759 ], "comparison": { "original": "That my my sister, I know it.", "retranscribed": "My sister. I know.", "reference_tokens": [ "that", "my", "my", "sister", "i", "know", "it" ], "hypothesis_tokens": [ "my", "sister", "i", "know" ], "counts": { "substitutions": 0, "deletions": 3, "insertions": 0, "hits": 4, "reference_words": 7, "hypothesis_words": 4, "edits": 3 }, "wer": 0.42857142857142855, "wer_percent": 42.857142857142854, "alignment": [ { "op": "delete", "reference": "that", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "delete", "reference": "my", "hypothesis": null, "reference_index": 1, "hypothesis_index": null }, { "op": "equal", "reference": "my", "hypothesis": "my", "reference_index": 2, "hypothesis_index": 0 }, { "op": "equal", "reference": "sister", "hypothesis": "sister", "reference_index": 3, "hypothesis_index": 1 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 4, "hypothesis_index": 2 }, { "op": "equal", "reference": "know", "hypothesis": "know", "reference_index": 5, "hypothesis_index": 3 }, { "op": "delete", "reference": "it", "hypothesis": null, "reference_index": 6, "hypothesis_index": null } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.4263, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Sad", "emotion_confidence": 0.7415180206298828, "duration_seconds": 1.1089999999999995, "mos": 3.6929, "audio_variant": "original", "original_transcript_raw": "I'd forgotten why I came down. ", "original_transcript": "I'd forgotten why I came down.", "retranscribed_transcript": "I'd forgotten why I came down.", "backend": "qwen", "emotion_analyzed_seconds": 1.109, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-056", "energy": { "value": 0.484375, "bucket": "low" }, "audio_url": "audio/utterance-056.wav", "spectrogram_url": "spectrograms/utterance-056.png", "waveform": [ 0.00831, 0.00986, 0.01216, 0.00766, 0.00957, 0.02764, 0.12422, 0.14002, 0.07135, 0.15097, 0.1073, 0.05053, 0.05507, 0.03546, 0.04162, 0.01873, 0.01878, 0.0159, 0.01812, 0.01426, 0.01578, 0.0157, 0.0185, 0.02144, 0.01854, 0.01537, 0.03132, 0.07226, 0.09987, 0.05231, 0.05324, 0.04461, 0.04427, 0.0309, 0.03393, 0.02307, 0.03163, 0.04641, 0.0337, 0.11111, 0.17779, 0.15444, 0.08611, 0.17813, 0.14385, 0.06756, 0.10532, 0.10998, 0.06386, 0.07195, 0.06206, 0.03589, 0.03145, 0.03782, 0.03802, 0.02767, 0.0195, 0.01475, 0.01251, 0.01551, 0.0153, 0.01709, 0.02606, 0.02253, 0.02415, 0.03901, 0.02801, 0.04349, 0.0434, 0.03129, 0.04288, 0.04359, 0.04281, 0.04168, 0.04074, 0.03515, 0.04402, 0.03897, 0.04343, 0.04638, 0.04335, 0.03183, 0.02863, 0.03992, 0.04019, 0.0368, 0.06143, 0.04519, 0.04887, 0.05046, 0.04448, 0.05591, 0.04137, 0.05061, 0.03555, 0.04275, 0.03521, 0.02311, 0.02195, 0.00792, 0.00845, 0.00505, 0.00432, 0.00407, 0.00586, 0.02297, 0.01645, 0.02361, 0.01488, 0.01031, 0.01416, 0.00771, 0.01158, 0.01241, 0.01372, 0.02533, 0.03215, 0.04727, 0.03946, 0.02961, 0.02885, 0.02002, 0.01638, 0.02003, 0.00797, 0.0208, 0.01056, 0.01048, 0.00652, 0.01286, 0.00952, 0.00782, 0.00682, 0.02766, 0.01019, 0.0063, 0.01134, 0.01372, 0.01145, 0.00858, 0.01038, 0.00995, 0.00933, 0.01691, 0.01601, 0.02142, 0.01856, 0.02409, 0.01472, 0.01882, 0.0117, 0.01993, 0.01826, 0.01775, 0.00772, 0.0104, 0.00818, 0.0108, 0.00775, 0.00967, 0.00547, 0.01006, 0.0058, 0.00408, 0.00352, 0.00495, 0.00381, 0.00469, 0.00416, 0.00335, 0.00407, 0.00242, 0.00292, 0.00188, 0.00318, 0.00195, 0.00228, 0.00399, 0.00305, 0.00127 ], "comparison": { "original": "I'd forgotten why I came down.", "retranscribed": "I'd forgotten why I came down.", "reference_tokens": [ "id", "forgotten", "why", "i", "came", "down" ], "hypothesis_tokens": [ "id", "forgotten", "why", "i", "came", "down" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 6, "reference_words": 6, "hypothesis_words": 6, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "id", "hypothesis": "id", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "forgotten", "hypothesis": "forgotten", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "why", "hypothesis": "why", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "came", "hypothesis": "came", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "down", "hypothesis": "down", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.17813, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Sad", "emotion_confidence": 0.4027872681617737, "duration_seconds": 3.6180000000000234, "mos": 3.0757, "audio_variant": "cleaned", "original_transcript_raw": "Let's be honest, painting can be a pain. This doesn't look good. ", "original_transcript": "Let's be honest, painting can be a pain. This doesn't look good.", "retranscribed_transcript": "Let's be honest: painting can be a pain. This doesn't look good.", "backend": "qwen", "emotion_analyzed_seconds": 3.618, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-057", "energy": { "value": 0.451171875, "bucket": "low" }, "audio_url": "audio/utterance-057.wav", "spectrogram_url": "spectrograms/utterance-057.png", "waveform": [ 0.01814, 0.00719, 0.00562, 0.11107, 0.26186, 0.27053, 0.35729, 0.62192, 0.59453, 0.33987, 0.18468, 0.06632, 0.03928, 0.0949, 0.1067, 0.10391, 0.00629, 0.00392, 0.0723, 0.26233, 0.23471, 0.13866, 0.12434, 0.11553, 0.15762, 0.11584, 0.15626, 0.22716, 0.2582, 0.18388, 0.22133, 0.15264, 0.09409, 0.10043, 0.13266, 0.10521, 0.14023, 0.11716, 0.09249, 0.04762, 0.07532, 0.08948, 0.10404, 0.05616, 0.02267, 0.02396, 0.01092, 0.01303, 0.01125, 0.00766, 0.007, 0.00844, 0.00812, 0.00701, 0.00791, 0.00853, 0.00643, 0.00833, 0.00516, 0.0059, 0.16828, 0.06529, 0.07432, 0.29774, 0.24539, 0.25446, 0.33472, 0.28591, 0.25505, 0.04357, 0.05287, 0.11128, 0.31533, 0.34142, 0.36518, 0.35773, 0.41773, 0.41539, 0.41294, 0.3243, 0.19131, 0.31511, 0.40006, 0.41712, 0.23503, 0.13535, 0.13552, 0.15031, 0.05751, 0.30132, 0.07604, 0.13485, 0.14523, 0.13188, 0.1027, 0.12951, 0.14269, 0.141, 0.17452, 0.15336, 0.04373, 0.01329, 0.00457, 0.13687, 0.09978, 0.21032, 0.16392, 0.16097, 0.12281, 0.08171, 0.11317, 0.08255, 0.12516, 0.04337, 0.07698, 0.04784, 0.07285, 0.05539, 0.08484, 0.03858, 0.06122, 0.07729, 0.06951, 0.07742, 0.0301, 0.03306, 0.01857, 0.01856, 0.01155, 0.01312, 0.00733, 0.0066, 0.00465, 0.00316, 0.00392, 0.00206, 0.00335, 0.00363, 0.00547, 0.00525, 0.11634, 0.12452, 0.08938, 0.03855, 0.05542, 0.04644, 0.05357, 0.00294, 0.24609, 0.41467, 0.52839, 0.3747, 0.32742, 0.25622, 0.09251, 0.04332, 0.10322, 0.18415, 0.19167, 0.16679, 0.1534, 0.13086, 0.132, 0.14817, 0.14064, 0.15299, 0.1339, 0.0083, 0.00324, 0.22167, 0.148, 0.22813, 0.23947, 0.18956, 0.17676, 0.17487, 0.08406, 0.14063, 0.03544, 0.02729 ], "comparison": { "original": "Let's be honest, painting can be a pain. This doesn't look good.", "retranscribed": "Let's be honest: painting can be a pain. This doesn't look good.", "reference_tokens": [ "lets", "be", "honest", "painting", "can", "be", "a", "pain", "this", "doesnt", "look", "good" ], "hypothesis_tokens": [ "lets", "be", "honest", "painting", "can", "be", "a", "pain", "this", "doesnt", "look", "good" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 12, "reference_words": 12, "hypothesis_words": 12, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "lets", "hypothesis": "lets", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "be", "hypothesis": "be", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "honest", "hypothesis": "honest", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "painting", "hypothesis": "painting", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "can", "hypothesis": "can", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "be", "hypothesis": "be", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "pain", "hypothesis": "pain", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "this", "hypothesis": "this", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "doesnt", "hypothesis": "doesnt", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "look", "hypothesis": "look", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "good", "hypothesis": "good", "reference_index": 11, "hypothesis_index": 11 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.62192, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Sad", "emotion_confidence": 0.25225916504859924, "duration_seconds": 1.0409999999999968, "mos": 3.3198, "audio_variant": "original", "original_transcript_raw": "Абсолю", "original_transcript": "Абсолю", "retranscribed_transcript": "I'm sorry, blue.", "backend": "qwen", "emotion_analyzed_seconds": 1.041, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-058", "energy": { "value": 0.5234375, "bucket": "medium" }, "audio_url": "audio/utterance-058.wav", "spectrogram_url": "spectrograms/utterance-058.png", "waveform": [ 0.06769, 0.05495, 0.14005, 0.37723, 0.09488, 0.07696, 0.29161, 0.35238, 0.38546, 0.33207, 0.27695, 0.30463, 0.25743, 0.28847, 0.28015, 0.24136, 0.19868, 0.17316, 0.17978, 0.11133, 0.08913, 0.04989, 0.06062, 0.05803, 0.04709, 0.08711, 0.0544, 0.09188, 0.0511, 0.06215, 0.0657, 0.07461, 0.06109, 0.05529, 0.06744, 0.07557, 0.05982, 0.0985, 0.11029, 0.08728, 0.09325, 0.0733, 0.08635, 0.0693, 0.0856, 0.11644, 0.08584, 0.0917, 0.05675, 0.04794, 0.06328, 0.08999, 0.25405, 0.28502, 0.27816, 0.26426, 0.24121, 0.25192, 0.19427, 0.21739, 0.19015, 0.17429, 0.14677, 0.12355, 0.16848, 0.12221, 0.09407, 0.1483, 0.10054, 0.09914, 0.11617, 0.10189, 0.11021, 0.14814, 0.15302, 0.18957, 0.16367, 0.1696, 0.19619, 0.13377, 0.22008, 0.16938, 0.20717, 0.19301, 0.22986, 0.16759, 0.20158, 0.25279, 0.22988, 0.22609, 0.22808, 0.19096, 0.17942, 0.20094, 0.2142, 0.17604, 0.18727, 0.17409, 0.18997, 0.18447, 0.17186, 0.19014, 0.17822, 0.16359, 0.19311, 0.15851, 0.17268, 0.18158, 0.14488, 0.16839, 0.15929, 0.17084, 0.12038, 0.1308, 0.10701, 0.07419, 0.0692, 0.04696, 0.04386, 0.05254, 0.0493, 0.03977, 0.03504, 0.04623, 0.05076, 0.03973, 0.04654, 0.04399, 0.04682, 0.04086, 0.04771, 0.04511, 0.0456, 0.03027, 0.05031, 0.05446, 0.05804, 0.06086, 0.04362, 0.0423, 0.03884, 0.03085, 0.04353, 0.0339, 0.03043, 0.02999, 0.02781, 0.02885, 0.04704, 0.04099, 0.05869, 0.04553, 0.02584, 0.02333, 0.02748, 0.02654, 0.03538, 0.04304, 0.041, 0.04023, 0.03601, 0.03466, 0.05268, 0.05615, 0.04143, 0.04841, 0.04477, 0.04356, 0.04698, 0.04708, 0.03908, 0.04261, 0.03676, 0.04022, 0.02995, 0.02672, 0.02969, 0.03833, 0.03189, 0.02511 ], "comparison": { "original": "Абсолю", "retranscribed": "I'm sorry, blue.", "reference_tokens": [ "абсолю" ], "hypothesis_tokens": [ "im", "sorry", "blue" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 2, "hits": 0, "reference_words": 1, "hypothesis_words": 3, "edits": 3 }, "wer": 3.0, "wer_percent": 300.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "im", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "sorry", "reference_index": null, "hypothesis_index": 1 }, { "op": "substitute", "reference": "абсолю", "hypothesis": "blue", "reference_index": 0, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.38546, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Sad", "emotion_confidence": 0.357054203748703, "duration_seconds": 3.05499999999995, "mos": 3.5112, "audio_variant": "cleaned", "original_transcript_raw": "We don't dur all our sick animals, mister kehoe. ", "original_transcript": "We don't dur all our sick animals, mister kehoe.", "retranscribed_transcript": "We don't do all our sick animals, Mister Keoh.", "backend": "qwen", "emotion_analyzed_seconds": 3.055, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-059", "energy": { "value": 0.5390625, "bucket": "medium" }, "audio_url": "audio/utterance-059.wav", "spectrogram_url": "spectrograms/utterance-059.png", "waveform": [ 0.02228, 0.02366, 0.00982, 0.01105, 0.00997, 0.01261, 0.03407, 0.03493, 0.04956, 0.0696, 0.07189, 0.08211, 0.10208, 0.12148, 0.15742, 0.18038, 0.20284, 0.25037, 0.28992, 0.26761, 0.27959, 0.28312, 0.28763, 0.29447, 0.14117, 0.11345, 0.07877, 0.06442, 0.05139, 0.12598, 0.29337, 0.40942, 0.7252, 0.60329, 0.39779, 0.40414, 0.27781, 0.19631, 0.16334, 0.14988, 0.16285, 0.1603, 0.11615, 0.08816, 0.06642, 0.15358, 0.15985, 0.28114, 0.4391, 0.4664, 0.34415, 0.26403, 0.18289, 0.20085, 0.16224, 0.17203, 0.23822, 0.33672, 0.30616, 0.24115, 0.27646, 0.29557, 0.3035, 0.34376, 0.3836, 0.37322, 0.28124, 0.26744, 0.24063, 0.21447, 0.26651, 0.22827, 0.22592, 0.24376, 0.2129, 0.22816, 0.19568, 0.21212, 0.14668, 0.12073, 0.08271, 0.10166, 0.11064, 0.1254, 0.10009, 0.09513, 0.09121, 0.05919, 0.04418, 0.21903, 0.35649, 0.32569, 0.11507, 0.04016, 0.00873, 0.00323, 0.19319, 0.07501, 0.2648, 0.32215, 0.32011, 0.3302, 0.2883, 0.30637, 0.3041, 0.29363, 0.31247, 0.32375, 0.31993, 0.37334, 0.34785, 0.2852, 0.24476, 0.23521, 0.21443, 0.20798, 0.22993, 0.18526, 0.18129, 0.18168, 0.18841, 0.21514, 0.22943, 0.23011, 0.18541, 0.16737, 0.1187, 0.0999, 0.04923, 0.12004, 0.24842, 0.27394, 0.27694, 0.24173, 0.19837, 0.18296, 0.07729, 0.08256, 0.06514, 0.02625, 0.00386, 0.1244, 0.07269, 0.07103, 0.01826, 0.00303, 0.00271, 0.14557, 0.09324, 0.13918, 0.20611, 0.24219, 0.25947, 0.24825, 0.2458, 0.23823, 0.22567, 0.24275, 0.24407, 0.23436, 0.25155, 0.23502, 0.21251, 0.21254, 0.1959, 0.19906, 0.18892, 0.19187, 0.13725, 0.09505, 0.07826, 0.08231, 0.07159, 0.06166, 0.06017, 0.05125, 0.04146, 0.02488, 0.01191, 0.013 ], "comparison": { "original": "We don't dur all our sick animals, mister kehoe.", "retranscribed": "We don't do all our sick animals, Mister Keoh.", "reference_tokens": [ "we", "dont", "dur", "all", "our", "sick", "animals", "mister", "kehoe" ], "hypothesis_tokens": [ "we", "dont", "do", "all", "our", "sick", "animals", "mister", "keoh" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 7, "reference_words": 9, "hypothesis_words": 9, "edits": 2 }, "wer": 0.2222222222222222, "wer_percent": 22.22222222222222, "alignment": [ { "op": "equal", "reference": "we", "hypothesis": "we", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "dont", "hypothesis": "dont", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "dur", "hypothesis": "do", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "all", "hypothesis": "all", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "our", "hypothesis": "our", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "sick", "hypothesis": "sick", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "animals", "hypothesis": "animals", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "mister", "hypothesis": "mister", "reference_index": 7, "hypothesis_index": 7 }, { "op": "substitute", "reference": "kehoe", "hypothesis": "keoh", "reference_index": 8, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.7252, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Sad", "emotion_confidence": 0.7008804678916931, "duration_seconds": 3.8559999999999945, "mos": 2.9207, "audio_variant": "cleaned", "original_transcript_raw": "Baby do have me, baby don't have me. ", "original_transcript": "Baby do have me, baby don't have me.", "retranscribed_transcript": "Baby, don't hurt me. Baby, don't hurt me.", "backend": "qwen", "emotion_analyzed_seconds": 3.856, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-060", "energy": { "value": 0.51953125, "bucket": "medium" }, "audio_url": "audio/utterance-060.wav", "spectrogram_url": "spectrograms/utterance-060.png", "waveform": [ 0.06959, 0.08336, 0.2349, 0.2337, 0.21983, 0.23815, 0.20059, 0.27217, 0.34956, 0.40909, 0.4398, 0.45311, 0.45022, 0.401, 0.3387, 0.31649, 0.17628, 0.11393, 0.1034, 0.22373, 0.24887, 0.25376, 0.24513, 0.12275, 0.09022, 0.40447, 0.34627, 0.30027, 0.29604, 0.3214, 0.30251, 0.26795, 0.17032, 0.10944, 0.09463, 0.1135, 0.08233, 0.16385, 0.21068, 0.24403, 0.24508, 0.19759, 0.15952, 0.11759, 0.08187, 0.04133, 0.03217, 0.01476, 0.00866, 0.00715, 0.00895, 0.00872, 0.14225, 0.26433, 0.28488, 0.29971, 0.28023, 0.27799, 0.27747, 0.23628, 0.21487, 0.19554, 0.16487, 0.15854, 0.12946, 0.10489, 0.11118, 0.08711, 0.07294, 0.04104, 0.03248, 0.02631, 0.01534, 0.00676, 0.00282, 0.00263, 0.00276, 0.00426, 0.00729, 0.01192, 0.01886, 0.01472, 0.01701, 0.0125, 0.01033, 0.0065, 0.00307, 0.00184, 0.00253, 0.00233, 0.00687, 0.05773, 0.30519, 0.31076, 0.27229, 0.22507, 0.3263, 0.36072, 0.35085, 0.38976, 0.35431, 0.32405, 0.31068, 0.29686, 0.28991, 0.10712, 0.10708, 0.14369, 0.20002, 0.18445, 0.17063, 0.12364, 0.09075, 0.33737, 0.30013, 0.29016, 0.30255, 0.31189, 0.32051, 0.31691, 0.15864, 0.11185, 0.08886, 0.09281, 0.11789, 0.1547, 0.26191, 0.27868, 0.27383, 0.22524, 0.17799, 0.1444, 0.0911, 0.07204, 0.03035, 0.01664, 0.14188, 0.19573, 0.20725, 0.22348, 0.23048, 0.25132, 0.24973, 0.22724, 0.21982, 0.21641, 0.1858, 0.153, 0.11757, 0.10938, 0.10798, 0.09643, 0.08024, 0.07136, 0.04857, 0.02992, 0.0228, 0.01024, 0.05084, 0.00753, 0.00444, 0.00285, 0.00195, 0.00158, 0.00125, 0.00119, 0.00119, 0.00138, 0.00155, 0.00091, 0.00051, 0.00151, 0.00119, 0.00061, 0.00068, 0.00114, 0.00111, 0.01104, 0.05568, 0.0795 ], "comparison": { "original": "Baby do have me, baby don't have me.", "retranscribed": "Baby, don't hurt me. Baby, don't hurt me.", "reference_tokens": [ "baby", "do", "have", "me", "baby", "dont", "have", "me" ], "hypothesis_tokens": [ "baby", "dont", "hurt", "me", "baby", "dont", "hurt", "me" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 8, "hypothesis_words": 8, "edits": 3 }, "wer": 0.375, "wer_percent": 37.5, "alignment": [ { "op": "equal", "reference": "baby", "hypothesis": "baby", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "do", "hypothesis": "dont", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "have", "hypothesis": "hurt", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "baby", "hypothesis": "baby", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "dont", "hypothesis": "dont", "reference_index": 5, "hypothesis_index": 5 }, { "op": "substitute", "reference": "have", "hypothesis": "hurt", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 7, "hypothesis_index": 7 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.45311, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Sad", "emotion_confidence": 0.5980132222175598, "duration_seconds": 2.029999999999994, "mos": 3.1653, "audio_variant": "cleaned", "original_transcript_raw": "I truly feel that half the time. ", "original_transcript": "I truly feel that half the time.", "retranscribed_transcript": "I truly feel that half the time.", "backend": "qwen", "emotion_analyzed_seconds": 2.03, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-061", "energy": { "value": 0.58203125, "bucket": "high" }, "audio_url": "audio/utterance-061.wav", "spectrogram_url": "spectrograms/utterance-061.png", "waveform": [ 0.24275, 0.30552, 0.32152, 0.31737, 0.25331, 0.2357, 0.24891, 0.22701, 0.19024, 0.17513, 0.13755, 0.10138, 0.04073, 0.0118, 0.00587, 0.00318, 0.0028, 0.00198, 0.03058, 0.06558, 0.205, 0.25216, 0.19929, 0.13387, 0.08688, 0.09344, 0.05661, 0.06103, 0.0571, 0.04052, 0.04451, 0.10414, 0.28955, 0.29953, 0.31713, 0.31688, 0.30897, 0.29865, 0.28333, 0.27326, 0.26881, 0.26895, 0.26801, 0.28727, 0.31801, 0.31419, 0.29796, 0.2303, 0.21111, 0.16578, 0.12543, 0.07505, 0.05413, 0.05351, 0.03767, 0.03738, 0.03048, 0.02806, 0.03053, 0.02511, 0.02192, 0.02465, 0.03592, 0.02789, 0.01932, 0.03874, 0.41311, 0.34866, 0.31076, 0.33267, 0.33124, 0.34439, 0.35129, 0.25397, 0.20971, 0.24838, 0.24215, 0.22543, 0.20046, 0.17661, 0.18146, 0.19505, 0.18003, 0.10214, 0.04627, 0.01868, 0.02004, 0.0666, 0.25355, 0.31306, 0.41661, 0.41653, 0.41796, 0.33622, 0.25382, 0.14935, 0.07754, 0.09838, 0.08139, 0.08913, 0.0982, 0.1188, 0.18416, 0.34575, 0.4349, 0.41896, 0.41582, 0.37108, 0.37146, 0.33796, 0.2542, 0.16471, 0.13997, 0.12117, 0.11905, 0.07928, 0.05028, 0.03051, 0.02239, 0.01116, 0.00688, 0.0034, 0.00224, 0.00201, 0.00119, 0.00112, 0.02616, 0.11303, 0.17372, 0.16093, 0.16044, 0.12607, 0.05059, 0.02464, 0.00724, 0.00471, 0.0035, 0.03095, 0.22968, 0.05333, 0.03421, 0.03285, 0.0389, 0.06934, 0.07193, 0.10448, 0.30106, 0.33715, 0.3452, 0.34177, 0.32563, 0.33033, 0.21279, 0.23189, 0.22553, 0.20869, 0.17418, 0.15494, 0.16652, 0.18794, 0.16038, 0.14154, 0.10881, 0.11469, 0.07747, 0.05454, 0.07343, 0.06192, 0.10479, 0.10701, 0.09903, 0.08779, 0.07237, 0.07442, 0.06806, 0.04706, 0.02639, 0.01924, 0.02872, 0.01992 ], "comparison": { "original": "I truly feel that half the time.", "retranscribed": "I truly feel that half the time.", "reference_tokens": [ "i", "truly", "feel", "that", "half", "the", "time" ], "hypothesis_tokens": [ "i", "truly", "feel", "that", "half", "the", "time" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 7, "reference_words": 7, "hypothesis_words": 7, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "truly", "hypothesis": "truly", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "feel", "hypothesis": "feel", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "half", "hypothesis": "half", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "time", "hypothesis": "time", "reference_index": 6, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.4349, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Sad", "emotion_confidence": 0.3971388339996338, "duration_seconds": 1.637999999999991, "mos": 3.542, "audio_variant": "cleaned", "original_transcript_raw": "It's so cold out. ", "original_transcript": "It's so cold out.", "retranscribed_transcript": "It's so cold out.", "backend": "qwen", "emotion_analyzed_seconds": 1.638, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-062", "energy": { "value": 0.59765625, "bucket": "high" }, "audio_url": "audio/utterance-062.wav", "spectrogram_url": "spectrograms/utterance-062.png", "waveform": [ 0.09622, 0.09473, 0.09009, 0.12273, 0.12649, 0.14855, 0.17209, 0.15988, 0.14221, 0.1507, 0.1439, 0.13937, 0.03616, 0.01045, 0.00559, 0.00154, 0.00159, 0.00683, 0.01241, 0.02028, 0.02911, 0.09442, 0.09631, 0.13386, 0.12036, 0.12385, 0.08768, 0.11503, 0.13131, 0.08075, 0.08217, 0.09249, 0.09194, 0.13894, 0.12623, 0.17093, 0.07774, 0.05724, 0.31928, 0.33274, 0.25893, 0.33699, 0.35611, 0.40259, 0.4072, 0.4466, 0.47425, 0.38441, 0.33381, 0.28669, 0.27181, 0.26839, 0.27841, 0.28668, 0.29263, 0.26182, 0.19557, 0.0871, 0.02542, 0.00411, 0.00263, 0.00172, 0.00096, 0.00177, 0.00157, 0.15247, 0.2266, 0.09461, 0.09282, 0.10475, 0.12225, 0.10549, 0.0918, 0.10441, 0.07557, 0.08327, 0.07197, 0.0809, 0.05812, 0.06184, 0.04134, 0.03928, 0.26904, 0.49635, 0.48171, 0.50137, 0.45503, 0.39573, 0.35953, 0.35971, 0.33434, 0.30238, 0.29698, 0.27858, 0.26712, 0.26544, 0.25306, 0.24571, 0.2257, 0.2345, 0.25036, 0.26719, 0.2596, 0.2332, 0.26883, 0.27486, 0.26943, 0.19792, 0.10555, 0.07633, 0.04871, 0.03429, 0.01485, 0.0214, 0.29273, 0.21137, 0.25275, 0.26447, 0.17798, 0.27393, 0.1566, 0.20478, 0.27178, 0.17427, 0.17696, 0.15546, 0.14412, 0.16672, 0.1656, 0.12795, 0.12734, 0.10789, 0.09189, 0.05661, 0.04003, 0.03117, 0.0489, 0.0242, 0.01241, 0.0065, 0.00893, 0.00288, 0.00247, 0.00204, 0.00171, 0.00086, 0.00181, 0.00093, 0.00058, 0.00101, 0.00112, 0.00085, 0.02861, 0.03377, 0.03032, 0.02354, 0.02706, 0.02628, 0.0174, 0.01699, 0.0081, 0.0053, 0.00309, 0.00169, 0.00174, 0.00194, 0.00154, 0.00106, 0.00088, 0.0009, 0.00092, 0.00107, 0.00081, 0.00046, 0.00414, 0.01127, 0.02411, 0.03887, 0.03031, 0.06264 ], "comparison": { "original": "It's so cold out.", "retranscribed": "It's so cold out.", "reference_tokens": [ "its", "so", "cold", "out" ], "hypothesis_tokens": [ "its", "so", "cold", "out" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 4, "reference_words": 4, "hypothesis_words": 4, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "its", "hypothesis": "its", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "so", "hypothesis": "so", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "cold", "hypothesis": "cold", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "out", "hypothesis": "out", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.50137, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Sad", "emotion_confidence": 0.545774519443512, "duration_seconds": 7.680000000000007, "mos": 2.9968, "audio_variant": "cleaned", "original_transcript_raw": "I've been told she's wearing a band of gold peggy sue got married not. ", "original_transcript": "I've been told she's wearing a band of gold peggy sue got married not.", "retranscribed_transcript": "I've been told that she's wearing a band of gold. Peggy Sue got married not.", "backend": "qwen", "emotion_analyzed_seconds": 7.68, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-063", "energy": { "value": 0.59765625, "bucket": "high" }, "audio_url": "audio/utterance-063.wav", "spectrogram_url": "spectrograms/utterance-063.png", "waveform": [ 0.0483, 0.45378, 0.53481, 0.42048, 0.28435, 0.26477, 0.38152, 0.37894, 0.24332, 0.04548, 0.05233, 0.09295, 0.30316, 0.25022, 0.26235, 0.31407, 0.27828, 0.14363, 0.14627, 0.07604, 0.07297, 0.1196, 0.24851, 0.23484, 0.23749, 0.23622, 0.18675, 0.11737, 0.1286, 0.13862, 0.13397, 0.16609, 0.15662, 0.04185, 0.00915, 0.01696, 0.01591, 0.0134, 0.00372, 0.00281, 0.07784, 0.09477, 0.31224, 0.34679, 0.36726, 0.32339, 0.31619, 0.3205, 0.29979, 0.23318, 0.1874, 0.2143, 0.25595, 0.29488, 0.27166, 0.20554, 0.18541, 0.10939, 0.12747, 0.17234, 0.16466, 0.26462, 0.3904, 0.40728, 0.36245, 0.32466, 0.31439, 0.26801, 0.25845, 0.20724, 0.09289, 0.32843, 0.33349, 0.07315, 0.06511, 0.05803, 0.45716, 0.38148, 0.34266, 0.29745, 0.27909, 0.26852, 0.23477, 0.19077, 0.10495, 0.10412, 0.09767, 0.3925, 0.2691, 0.22905, 0.26335, 0.28505, 0.28109, 0.07623, 0.09895, 0.04553, 0.32002, 0.32236, 0.38386, 0.31369, 0.30641, 0.30512, 0.23593, 0.23178, 0.20762, 0.18611, 0.17415, 0.1685, 0.13492, 0.08712, 0.11861, 0.06622, 0.00755, 0.01315, 0.01963, 0.01579, 0.02075, 0.01409, 0.00631, 0.00115, 0.05282, 0.20289, 0.40931, 0.30783, 0.4847, 0.6192, 0.04554, 0.16367, 0.18534, 0.2049, 0.20939, 0.20385, 0.15126, 0.09665, 0.12015, 0.13698, 0.1955, 0.2275, 0.2366, 0.22897, 0.22369, 0.21649, 0.19275, 0.08706, 0.03491, 0.1946, 0.35828, 0.64629, 0.30525, 0.30165, 0.35112, 0.35331, 0.28785, 0.09943, 0.1098, 0.12007, 0.2702, 0.22787, 0.2256, 0.21422, 0.24522, 0.28785, 0.32859, 0.25623, 0.23237, 0.26059, 0.24333, 0.17651, 0.11586, 0.11742, 0.1134, 0.26716, 0.30184, 0.30826, 0.29014, 0.34208, 0.13705, 0.16, 0.16716, 0.24461 ], "comparison": { "original": "I've been told she's wearing a band of gold peggy sue got married not.", "retranscribed": "I've been told that she's wearing a band of gold. Peggy Sue got married not.", "reference_tokens": [ "ive", "been", "told", "shes", "wearing", "a", "band", "of", "gold", "peggy", "sue", "got", "married", "not" ], "hypothesis_tokens": [ "ive", "been", "told", "that", "shes", "wearing", "a", "band", "of", "gold", "peggy", "sue", "got", "married", "not" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 14, "reference_words": 14, "hypothesis_words": 15, "edits": 1 }, "wer": 0.07142857142857142, "wer_percent": 7.142857142857142, "alignment": [ { "op": "equal", "reference": "ive", "hypothesis": "ive", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "been", "hypothesis": "been", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "told", "hypothesis": "told", "reference_index": 2, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "that", "reference_index": null, "hypothesis_index": 3 }, { "op": "equal", "reference": "shes", "hypothesis": "shes", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "wearing", "hypothesis": "wearing", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "band", "hypothesis": "band", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 7, "hypothesis_index": 8 }, { "op": "equal", "reference": "gold", "hypothesis": "gold", "reference_index": 8, "hypothesis_index": 9 }, { "op": "equal", "reference": "peggy", "hypothesis": "peggy", "reference_index": 9, "hypothesis_index": 10 }, { "op": "equal", "reference": "sue", "hypothesis": "sue", "reference_index": 10, "hypothesis_index": 11 }, { "op": "equal", "reference": "got", "hypothesis": "got", "reference_index": 11, "hypothesis_index": 12 }, { "op": "equal", "reference": "married", "hypothesis": "married", "reference_index": 12, "hypothesis_index": 13 }, { "op": "equal", "reference": "not", "hypothesis": "not", "reference_index": 13, "hypothesis_index": 14 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.64629, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Surprised", "emotion_confidence": 0.6483603119850159, "duration_seconds": 1.3829999999999956, "mos": 3.3535, "audio_variant": "cleaned", "original_transcript_raw": "Why is that? I don't know. ", "original_transcript": "Why is that? I don't know.", "retranscribed_transcript": "Why is that? I don't know.", "backend": "qwen", "emotion_analyzed_seconds": 1.383, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-064", "energy": { "value": 0.4765625, "bucket": "low" }, "audio_url": "audio/utterance-064.wav", "spectrogram_url": "spectrograms/utterance-064.png", "waveform": [ 0.02205, 0.04741, 0.03626, 0.08539, 0.14013, 0.15287, 0.1746, 0.18254, 0.18773, 0.19075, 0.18844, 0.21308, 0.20684, 0.21347, 0.20214, 0.21786, 0.18673, 0.14518, 0.15909, 0.14919, 0.14911, 0.13052, 0.14685, 0.13854, 0.1526, 0.16203, 0.15185, 0.15379, 0.14858, 0.14917, 0.0954, 0.06914, 0.04256, 0.03582, 0.0268, 0.01956, 0.01809, 0.02586, 0.01738, 0.01932, 0.02009, 0.01597, 0.0227, 0.02765, 0.03805, 0.03047, 0.02156, 0.03165, 0.21309, 0.24553, 0.21663, 0.18045, 0.2145, 0.1971, 0.16965, 0.15413, 0.14119, 0.11574, 0.09125, 0.11091, 0.10666, 0.10511, 0.06305, 0.08314, 0.09906, 0.07687, 0.06372, 0.07497, 0.07275, 0.04302, 0.02553, 0.0247, 0.01215, 0.00853, 0.00588, 0.00264, 0.00289, 0.00256, 0.00317, 0.00381, 0.00542, 0.05562, 0.08491, 0.07389, 0.088, 0.08232, 0.09104, 0.09568, 0.3467, 0.4244, 0.33186, 0.24346, 0.22509, 0.21242, 0.14727, 0.18398, 0.08768, 0.09047, 0.12518, 0.09063, 0.21617, 0.27934, 0.23678, 0.27256, 0.239, 0.20205, 0.22181, 0.2572, 0.25803, 0.27666, 0.28487, 0.2857, 0.3042, 0.31708, 0.33317, 0.33773, 0.25486, 0.28335, 0.27981, 0.27359, 0.28846, 0.31928, 0.28801, 0.50279, 0.6265, 0.6127, 0.6231, 0.54687, 0.46323, 0.49834, 0.48866, 0.34981, 0.31978, 0.27653, 0.2433, 0.24131, 0.23875, 0.21299, 0.2039, 0.19729, 0.19322, 0.18892, 0.18937, 0.17893, 0.13606, 0.11416, 0.0936, 0.05315, 0.01357, 0.01077, 0.01359, 0.00918, 0.00445, 0.00285, 0.00336, 0.00137, 0.00099, 0.00048, 0.00031, 0.00077, 0.00056, 0.00024, 0.00018, 0.00016, 0.00015, 8e-05, 0.0001, 0.0001, 0.0001, 8e-05, 7e-05, 0.00013, 8e-05, 0.00064, 0.00299, 0.00581, 0.00648, 0.01442, 0.01464, 0.00881 ], "comparison": { "original": "Why is that? I don't know.", "retranscribed": "Why is that? I don't know.", "reference_tokens": [ "why", "is", "that", "i", "dont", "know" ], "hypothesis_tokens": [ "why", "is", "that", "i", "dont", "know" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 6, "reference_words": 6, "hypothesis_words": 6, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "why", "hypothesis": "why", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "is", "hypothesis": "is", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "that", "hypothesis": "that", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "i", "hypothesis": "i", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "dont", "hypothesis": "dont", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "know", "hypothesis": "know", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.6265, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Surprised", "emotion_confidence": 0.5746307373046875, "duration_seconds": 1.671999999999997, "mos": 3.2861, "audio_variant": "cleaned", "original_transcript_raw": "She called you at the movies. ", "original_transcript": "She called you at the movies.", "retranscribed_transcript": "She called you at the movies.", "backend": "qwen", "emotion_analyzed_seconds": 1.672, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-065", "energy": { "value": 0.5078125, "bucket": "low" }, "audio_url": "audio/utterance-065.wav", "spectrogram_url": "spectrograms/utterance-065.png", "waveform": [ 0.0125, 0.01267, 0.01819, 0.01796, 0.02414, 0.03997, 0.03526, 0.03923, 0.03535, 0.04582, 0.04645, 0.03963, 0.03968, 0.03861, 0.05424, 0.05435, 0.04551, 0.03247, 0.02932, 0.02305, 0.01878, 0.01101, 0.00455, 0.00088, 0.00027, 0.00015, 0.00012, 0.03707, 0.03104, 0.09212, 0.07436, 0.09089, 0.06044, 0.0323, 0.03845, 0.04786, 0.04369, 0.03772, 0.02804, 0.01748, 0.02757, 0.02168, 0.00916, 0.01392, 0.01694, 0.02723, 0.03887, 0.04636, 0.05274, 0.03548, 0.02731, 0.02075, 0.00704, 0.00303, 0.00389, 0.01147, 0.01907, 0.02746, 0.04081, 0.04472, 0.06188, 0.04257, 0.0238, 0.01648, 0.00759, 0.00421, 0.02297, 0.04141, 0.05036, 0.05724, 0.05363, 0.05447, 0.05781, 0.05732, 0.0554, 0.04768, 0.03643, 0.02561, 0.00982, 0.00408, 0.00178, 0.00038, 7e-05, 5e-05, 4e-05, 0.00019, 0.00888, 0.02874, 0.01993, 0.04229, 0.04816, 0.03734, 0.02995, 0.03213, 0.03612, 0.03802, 0.03873, 0.04077, 0.04203, 0.04174, 0.03866, 0.03835, 0.04167, 0.04924, 0.05205, 0.04377, 0.04771, 0.05354, 0.05388, 0.05477, 0.05877, 0.05815, 0.05196, 0.04918, 0.04961, 0.05368, 0.05149, 0.05648, 0.05739, 0.05455, 0.05324, 0.04022, 0.03359, 0.02659, 0.02255, 0.02405, 0.02814, 0.07638, 0.09124, 0.08706, 0.08802, 0.07488, 0.07742, 0.09703, 0.09867, 0.08002, 0.08252, 0.08256, 0.06696, 0.06452, 0.05754, 0.06252, 0.05813, 0.05124, 0.04764, 0.04593, 0.05701, 0.06053, 0.05917, 0.05631, 0.0456, 0.04151, 0.05146, 0.04141, 0.0493, 0.03959, 0.03486, 0.02915, 0.02789, 0.03068, 0.02812, 0.0242, 0.01783, 0.01496, 0.01188, 0.01042, 0.00542, 0.00517, 0.00205, 0.00126, 0.00051, 0.00016, 6e-05, 6e-05, 0.00038, 0.00164, 0.00355, 0.00465, 0.00764, 0.01018 ], "comparison": { "original": "She called you at the movies.", "retranscribed": "She called you at the movies.", "reference_tokens": [ "she", "called", "you", "at", "the", "movies" ], "hypothesis_tokens": [ "she", "called", "you", "at", "the", "movies" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 6, "reference_words": 6, "hypothesis_words": 6, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "she", "hypothesis": "she", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "called", "hypothesis": "called", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "you", "hypothesis": "you", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "at", "hypothesis": "at", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "movies", "hypothesis": "movies", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.09867, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Surprised", "emotion_confidence": 0.30561256408691406, "duration_seconds": 1.007000000000005, "mos": 2.947, "audio_variant": "cleaned", "original_transcript_raw": "Can't she call me. ", "original_transcript": "Can't she call me.", "retranscribed_transcript": "Is she calling?", "backend": "qwen", "emotion_analyzed_seconds": 1.007, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-066", "energy": { "value": 0.482421875, "bucket": "low" }, "audio_url": "audio/utterance-066.wav", "spectrogram_url": "spectrograms/utterance-066.png", "waveform": [ 0.02014, 0.01935, 0.02069, 0.0173, 0.01471, 0.01048, 0.00823, 0.00763, 0.00366, 0.00299, 0.01066, 0.00958, 0.01633, 0.01781, 0.01547, 0.0142, 0.01236, 0.01296, 0.01559, 0.01325, 0.01333, 0.01549, 0.0143, 0.01532, 0.01671, 0.01027, 0.01301, 0.01015, 0.01118, 0.01389, 0.00899, 0.01515, 0.01959, 0.01034, 0.01515, 0.01809, 0.02263, 0.02403, 0.03298, 0.02444, 0.03078, 0.04208, 0.02863, 0.03513, 0.02351, 0.02428, 0.03384, 0.05358, 0.06438, 0.06787, 0.06821, 0.06045, 0.05452, 0.04394, 0.02945, 0.01454, 0.01034, 0.00938, 0.00753, 0.00618, 0.00581, 0.00523, 0.00624, 0.00549, 0.00362, 0.0026, 0.00179, 0.00589, 0.03668, 0.0195, 0.02585, 0.01027, 0.01544, 0.00776, 0.01483, 0.02682, 0.03175, 0.02707, 0.02996, 0.03575, 0.02903, 0.03181, 0.02476, 0.01902, 0.0198, 0.01997, 0.01865, 0.02221, 0.02172, 0.02203, 0.02829, 0.02106, 0.02498, 0.02188, 0.01825, 0.01872, 0.01635, 0.01438, 0.01977, 0.02477, 0.02416, 0.02452, 0.02422, 0.02864, 0.03618, 0.03383, 0.03652, 0.03707, 0.03646, 0.03503, 0.03081, 0.02814, 0.02599, 0.02497, 0.02524, 0.02964, 0.02787, 0.02915, 0.02684, 0.02475, 0.02328, 0.01695, 0.01169, 0.01035, 0.00525, 0.00505, 0.00514, 0.00497, 0.00261, 0.0032, 0.00252, 0.00236, 0.00256, 0.00249, 0.00272, 0.00228, 0.00255, 0.00282, 0.00278, 0.00295, 0.00311, 0.00212, 0.00199, 0.002, 0.00137, 0.00148, 0.0018, 0.00212, 0.00158, 0.0012, 0.00108, 0.0015, 0.0009, 0.00098, 0.0006, 0.00085, 0.0008, 0.00089, 0.00046, 0.00066, 0.00051, 0.00036, 0.0004, 0.00033, 0.00038, 0.00026, 0.00032, 0.00027, 0.00018, 0.00027, 0.00018, 0.00128, 0.00298, 0.00416, 0.0042, 0.00704, 0.00742, 0.00924, 0.01022, 0.01441 ], "comparison": { "original": "Can't she call me.", "retranscribed": "Is she calling?", "reference_tokens": [ "cant", "she", "call", "me" ], "hypothesis_tokens": [ "is", "she", "calling" ], "counts": { "substitutions": 2, "deletions": 1, "insertions": 0, "hits": 1, "reference_words": 4, "hypothesis_words": 3, "edits": 3 }, "wer": 0.75, "wer_percent": 75.0, "alignment": [ { "op": "substitute", "reference": "cant", "hypothesis": "is", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "she", "hypothesis": "she", "reference_index": 1, "hypothesis_index": 1 }, { "op": "delete", "reference": "call", "hypothesis": null, "reference_index": 2, "hypothesis_index": null }, { "op": "substitute", "reference": "me", "hypothesis": "calling", "reference_index": 3, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.06821, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Surprised", "emotion_confidence": 0.43842893838882446, "duration_seconds": 2.201999999999998, "mos": 2.8542, "audio_variant": "cleaned", "original_transcript_raw": "What duffy what", "original_transcript": "What duffy what", "retranscribed_transcript": "What nothing. What.", "backend": "qwen", "emotion_analyzed_seconds": 2.202, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-067", "energy": { "value": 0.55859375, "bucket": "medium" }, "audio_url": "audio/utterance-067.wav", "spectrogram_url": "spectrograms/utterance-067.png", "waveform": [ 0.03582, 0.03246, 0.0145, 0.01674, 0.00631, 0.20432, 0.28778, 0.09764, 0.19676, 0.13065, 0.11682, 0.14346, 0.2057, 0.17365, 0.1758, 0.16101, 0.01932, 0.0157, 0.0065, 0.00315, 0.00136, 0.00089, 0.0008, 0.00097, 0.00107, 0.00055, 0.00064, 0.00353, 0.00403, 0.0016, 0.00186, 0.00063, 0.00201, 0.00506, 0.13404, 0.15655, 0.19057, 0.1256, 0.21442, 0.09523, 0.16161, 0.13505, 0.02044, 0.01301, 0.01583, 0.02749, 0.03177, 0.02796, 0.0344, 0.01946, 0.14593, 0.20393, 0.1457, 0.13315, 0.1044, 0.08513, 0.05711, 0.02664, 0.00792, 0.00342, 0.00219, 0.00117, 0.00151, 0.0023, 0.00308, 0.00331, 0.00418, 0.004, 0.00513, 0.00443, 0.00611, 0.00553, 0.0056, 0.00553, 0.0056, 0.00521, 0.0054, 0.00518, 0.00455, 0.00388, 0.00432, 0.0043, 0.00436, 0.00305, 0.0032, 0.00296, 0.00293, 0.00201, 0.00194, 0.00237, 0.00194, 0.00176, 0.00151, 0.00221, 0.0018, 0.00194, 0.00136, 0.00115, 0.00158, 0.00183, 0.0024, 0.00227, 0.09519, 0.22628, 0.29862, 0.46287, 0.67517, 0.66209, 0.48107, 0.50068, 0.58455, 0.44073, 0.23399, 0.0972, 0.05409, 0.03208, 0.01053, 0.00522, 0.00305, 0.00155, 0.0012, 0.00062, 0.0005, 0.00053, 0.00066, 0.00096, 0.00067, 0.00077, 0.00042, 0.00039, 0.00064, 0.00075, 0.00062, 0.00081, 0.00079, 0.00072, 0.00077, 0.00059, 0.00085, 0.08723, 0.15779, 0.07994, 0.03398, 0.04656, 0.03355, 0.03672, 0.03139, 0.02716, 0.03427, 0.02161, 0.02872, 0.02447, 0.02035, 0.02626, 0.02008, 0.01894, 0.01727, 0.01929, 0.01867, 0.01648, 0.01187, 0.01555, 0.01331, 0.0114, 0.01099, 0.01029, 0.0104, 0.01062, 0.00678, 0.00842, 0.00703, 0.00595, 0.00698, 0.00513, 0.00355, 0.00164, 0.00566, 0.02243, 0.02955, 0.03571 ], "comparison": { "original": "What duffy what", "retranscribed": "What nothing. What.", "reference_tokens": [ "what", "duffy", "what" ], "hypothesis_tokens": [ "what", "nothing", "what" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 3, "hypothesis_words": 3, "edits": 1 }, "wer": 0.3333333333333333, "wer_percent": 33.33333333333333, "alignment": [ { "op": "equal", "reference": "what", "hypothesis": "what", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "duffy", "hypothesis": "nothing", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "what", "hypothesis": "what", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.67517, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Surprised", "emotion_confidence": 0.4252749979496002, "duration_seconds": 1.3999999999999986, "mos": 2.8362, "audio_variant": "cleaned", "original_transcript_raw": "I curious though. ", "original_transcript": "I curious though.", "retranscribed_transcript": "I'm curious, though.", "backend": "qwen", "emotion_analyzed_seconds": 1.4, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-068", "energy": { "value": 0.5703125, "bucket": "medium" }, "audio_url": "audio/utterance-068.wav", "spectrogram_url": "spectrograms/utterance-068.png", "waveform": [ 0.40423, 0.27796, 0.28065, 0.26452, 0.16308, 0.16313, 0.19144, 0.18239, 0.19552, 0.1409, 0.09895, 0.09979, 0.09506, 0.08647, 0.0889, 0.08409, 0.06699, 0.03327, 0.01898, 0.00751, 0.00225, 0.00133, 0.00117, 0.00076, 0.00066, 0.00071, 0.00068, 0.00034, 0.0004, 0.00053, 0.0003, 0.0005, 0.00034, 0.00025, 0.0005, 0.00042, 0.05533, 0.05887, 0.02672, 0.01349, 0.02295, 0.02981, 0.03552, 0.03441, 0.03418, 0.04093, 0.063, 0.06525, 0.0463, 0.05415, 0.0555, 0.05409, 0.03853, 0.08231, 0.21775, 0.23594, 0.25056, 0.25236, 0.21631, 0.20969, 0.26658, 0.24552, 0.24928, 0.25232, 0.19331, 0.13838, 0.19794, 0.22349, 0.18282, 0.18117, 0.1474, 0.12215, 0.09467, 0.09865, 0.10637, 0.12339, 0.14778, 0.14048, 0.1403, 0.1872, 0.17782, 0.16809, 0.16615, 0.17199, 0.18531, 0.18819, 0.24144, 0.24595, 0.18888, 0.15425, 0.21488, 0.22485, 0.13191, 0.1238, 0.09015, 0.07105, 0.04613, 0.03917, 0.04102, 0.04072, 0.04145, 0.05064, 0.04614, 0.04925, 0.06122, 0.03635, 0.03311, 0.03945, 0.0242, 0.02199, 0.01212, 0.00569, 0.00343, 0.00213, 0.00173, 0.00164, 0.00202, 0.00213, 0.00336, 0.00514, 0.07739, 0.20496, 0.26238, 0.31432, 0.31983, 0.33319, 0.31771, 0.29318, 0.25279, 0.25605, 0.23995, 0.25255, 0.25276, 0.25528, 0.24605, 0.27504, 0.26491, 0.2793, 0.2986, 0.29848, 0.32368, 0.31083, 0.30817, 0.29241, 0.29372, 0.24624, 0.24341, 0.25827, 0.21446, 0.27199, 0.2563, 0.22609, 0.1781, 0.18319, 0.159, 0.14976, 0.16522, 0.13321, 0.14796, 0.13144, 0.12305, 0.07446, 0.05769, 0.06079, 0.05158, 0.03599, 0.02637, 0.02259, 0.01471, 0.01211, 0.00873, 0.006, 0.00422, 0.00677, 0.02043, 0.02874, 0.04315, 0.0663, 0.0797, 0.0521 ], "comparison": { "original": "I curious though.", "retranscribed": "I'm curious, though.", "reference_tokens": [ "i", "curious", "though" ], "hypothesis_tokens": [ "im", "curious", "though" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 3, "hypothesis_words": 3, "edits": 1 }, "wer": 0.3333333333333333, "wer_percent": 33.33333333333333, "alignment": [ { "op": "substitute", "reference": "i", "hypothesis": "im", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "curious", "hypothesis": "curious", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "though", "hypothesis": "though", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.40423, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Surprised", "emotion_confidence": 0.48385897278785706, "duration_seconds": 2.1329999999999814, "mos": 3.4174, "audio_variant": "cleaned", "original_transcript_raw": "Anyone else care for a glass of water? ", "original_transcript": "Anyone else care for a glass of water?", "retranscribed_transcript": "Anyone else care for a glass of water?", "backend": "qwen", "emotion_analyzed_seconds": 2.133, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-069", "energy": { "value": 0.52734375, "bucket": "medium" }, "audio_url": "audio/utterance-069.wav", "spectrogram_url": "spectrograms/utterance-069.png", "waveform": [ 0.09105, 0.07687, 0.09676, 0.19059, 0.23291, 0.29476, 0.27058, 0.26708, 0.24184, 0.23339, 0.22406, 0.22974, 0.20756, 0.19739, 0.22348, 0.28605, 0.33498, 0.37736, 0.38337, 0.34572, 0.39171, 0.39721, 0.2569, 0.26388, 0.28664, 0.28647, 0.40904, 0.44048, 0.50669, 0.46708, 0.43843, 0.39877, 0.39713, 0.4092, 0.34561, 0.33178, 0.28196, 0.21737, 0.16642, 0.09547, 0.05056, 0.04725, 0.06675, 0.05268, 0.03499, 0.06717, 0.05616, 0.05634, 0.09938, 0.05796, 0.00862, 0.00248, 0.00144, 0.20278, 0.1392, 0.06313, 0.10055, 0.10583, 0.20002, 0.19912, 0.1943, 0.19263, 0.18813, 0.2345, 0.17823, 0.19022, 0.18402, 0.20049, 0.17907, 0.12076, 0.04523, 0.03687, 0.03157, 0.03703, 0.03968, 0.03631, 0.03782, 0.09118, 0.12951, 0.12574, 0.14382, 0.16058, 0.15292, 0.1719, 0.20146, 0.22025, 0.21118, 0.23834, 0.24363, 0.06249, 0.00634, 0.00196, 0.07601, 0.23177, 0.17967, 0.25952, 0.3253, 0.26899, 0.29027, 0.22984, 0.25554, 0.25547, 0.31067, 0.3277, 0.32974, 0.34405, 0.37375, 0.26067, 0.2245, 0.16334, 0.13288, 0.12065, 0.04597, 0.02953, 0.01769, 0.02271, 0.03899, 0.03305, 0.02438, 0.03726, 0.03546, 0.05633, 0.03791, 0.07404, 0.10331, 0.08735, 0.08209, 0.06779, 0.07207, 0.07496, 0.06766, 0.0627, 0.04223, 0.03967, 0.06398, 0.07383, 0.08493, 0.09402, 0.10644, 0.09628, 0.10593, 0.08875, 0.09801, 0.11403, 0.14397, 0.15701, 0.16309, 0.16922, 0.15994, 0.1566, 0.16481, 0.14929, 0.08663, 0.04964, 0.12071, 0.14914, 0.16388, 0.138, 0.11905, 0.11343, 0.10462, 0.08108, 0.07162, 0.05329, 0.05187, 0.0421, 0.02856, 0.03885, 0.03167, 0.01574, 0.01606, 0.01074, 0.00769, 0.00614, 0.00252, 0.00191, 0.00792, 0.00718, 0.01404, 0.01618 ], "comparison": { "original": "Anyone else care for a glass of water?", "retranscribed": "Anyone else care for a glass of water?", "reference_tokens": [ "anyone", "else", "care", "for", "a", "glass", "of", "water" ], "hypothesis_tokens": [ "anyone", "else", "care", "for", "a", "glass", "of", "water" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 8, "reference_words": 8, "hypothesis_words": 8, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "anyone", "hypothesis": "anyone", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "else", "hypothesis": "else", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "care", "hypothesis": "care", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "for", "hypothesis": "for", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "glass", "hypothesis": "glass", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "of", "hypothesis": "of", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "water", "hypothesis": "water", "reference_index": 7, "hypothesis_index": 7 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.50669, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Surprised", "emotion_confidence": 0.8942352533340454, "duration_seconds": 1.740000000000009, "mos": 3.6739, "audio_variant": "cleaned", "original_transcript_raw": "Dude", "original_transcript": "Dude", "retranscribed_transcript": "Oh, doom.", "backend": "qwen", "emotion_analyzed_seconds": 1.74, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-070", "energy": { "value": 0.7890625, "bucket": "high" }, "audio_url": "audio/utterance-070.wav", "spectrogram_url": "spectrograms/utterance-070.png", "waveform": [ 0.02244, 0.03674, 0.01737, 0.00561, 0.00546, 0.00095, 0.00055, 0.00091, 0.00077, 0.00083, 0.00062, 0.0015, 0.00155, 0.00126, 0.00162, 0.0009, 0.00175, 0.00179, 0.00204, 0.00128, 0.00098, 0.00138, 0.00082, 0.00042, 0.00073, 0.00062, 0.00102, 0.00168, 0.00188, 0.00259, 0.00367, 0.00777, 0.0415, 0.10668, 0.11302, 0.19443, 0.29059, 0.37195, 0.36017, 0.41027, 0.48415, 0.47701, 0.45742, 0.36177, 0.3746, 0.34102, 0.34784, 0.37798, 0.46481, 0.48219, 0.47811, 0.25298, 0.32994, 0.33216, 0.30336, 0.33607, 0.37264, 0.35794, 0.35988, 0.33915, 0.34264, 0.32055, 0.32734, 0.31198, 0.29496, 0.29402, 0.27825, 0.24699, 0.24896, 0.26041, 0.24764, 0.23976, 0.21427, 0.19122, 0.16839, 0.15733, 0.14976, 0.15564, 0.16223, 0.17908, 0.19776, 0.19794, 0.17275, 0.20837, 0.20765, 0.23421, 0.2278, 0.23196, 0.21196, 0.20907, 0.22759, 0.24663, 0.24173, 0.22597, 0.22385, 0.18854, 0.19041, 0.19778, 0.20586, 0.2309, 0.24712, 0.24536, 0.27328, 0.27823, 0.3101, 0.29415, 0.26713, 0.26759, 0.25886, 0.29042, 0.22672, 0.09123, 0.07679, 0.06524, 0.05632, 0.04812, 0.02558, 0.10273, 0.09732, 0.12799, 0.17508, 0.34304, 0.37791, 0.37579, 0.37077, 0.28636, 0.21662, 0.24957, 0.27109, 0.26037, 0.27624, 0.28682, 0.26285, 0.27598, 0.26452, 0.2817, 0.31362, 0.35748, 0.38996, 0.32077, 0.24504, 0.31401, 0.3506, 0.38811, 0.43478, 0.43047, 0.41263, 0.35746, 0.2827, 0.28073, 0.28128, 0.28584, 0.20019, 0.17098, 0.10486, 0.11364, 0.11683, 0.07999, 0.08287, 0.09564, 0.08016, 0.06643, 0.05185, 0.04094, 0.0305, 0.01987, 0.0163, 0.00606, 0.00303, 0.0019, 0.00084, 0.00032, 0.00026, 9e-05, 0.00037, 0.00406, 0.01141, 0.01611, 0.01466, 0.01791 ], "comparison": { "original": "Dude", "retranscribed": "Oh, doom.", "reference_tokens": [ "dude" ], "hypothesis_tokens": [ "oh", "doom" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 1, "hits": 0, "reference_words": 1, "hypothesis_words": 2, "edits": 2 }, "wer": 2.0, "wer_percent": 200.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "oh", "reference_index": null, "hypothesis_index": 0 }, { "op": "substitute", "reference": "dude", "hypothesis": "doom", "reference_index": 0, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.48415, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Surprised", "emotion_confidence": 0.7359804511070251, "duration_seconds": 8.130999999999972, "mos": 3.6657, "audio_variant": "cleaned", "original_transcript_raw": "Chance. Oh no, to hear a voice that's very rare. If there is a spirit present, he'll speak to us by tapping with the tape. ", "original_transcript": "Chance. Oh no, to hear a voice that's very rare. If there is a spirit present, he'll speak to us by tapping with the tape.", "retranscribed_transcript": "Chance. Oh no, to hear a voice that's very rare. If there is a spirit present, he'll speak to us by tapping with the tin.", "backend": "qwen", "emotion_analyzed_seconds": 8.131, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-071", "energy": { "value": 0.6015625, "bucket": "high" }, "audio_url": "audio/utterance-071.wav", "spectrogram_url": "spectrograms/utterance-071.png", "waveform": [ 0.03689, 0.17887, 0.3881, 0.36649, 0.24836, 0.24627, 0.14223, 0.04261, 0.03434, 0.07342, 0.03253, 0.02571, 0.00366, 0.0012, 0.00034, 0.00011, 6e-05, 0.41038, 0.40966, 0.30792, 0.21621, 0.13373, 0.18067, 0.23553, 0.30666, 0.3356, 0.29093, 0.25388, 0.19942, 0.17503, 0.06134, 0.01724, 0.00575, 0.00329, 0.00242, 0.00114, 0.0003, 0.07845, 0.20945, 0.18102, 0.11185, 0.03103, 0.07644, 0.31949, 0.34622, 0.37389, 0.38835, 0.29391, 0.27159, 0.01281, 0.17621, 0.27037, 0.36165, 0.33218, 0.18048, 0.07305, 0.01032, 0.18465, 0.10522, 0.02695, 0.06776, 0.18102, 0.22099, 0.12836, 0.16039, 0.17854, 0.11793, 0.144, 0.24037, 0.28873, 0.2482, 0.21307, 0.18309, 0.1798, 0.12138, 0.04797, 0.00498, 0.00382, 0.00421, 0.00461, 0.00537, 0.00558, 0.00472, 0.00565, 0.00805, 0.01001, 0.00984, 0.00558, 0.0241, 0.1915, 0.16861, 0.0442, 0.17133, 0.18989, 0.24393, 0.18172, 0.19993, 0.30484, 0.26352, 0.13791, 0.21365, 0.21318, 0.16671, 0.04734, 0.01077, 0.133, 0.20658, 0.2353, 0.2315, 0.06979, 0.00081, 0.22753, 0.4081, 0.23397, 0.13797, 0.19471, 0.20658, 0.18251, 0.00904, 0.03325, 0.03264, 0.03268, 0.03317, 0.02059, 0.00547, 0.15004, 0.18258, 0.11475, 0.09093, 0.05338, 0.04131, 0.01741, 0.05116, 0.26292, 0.30569, 0.164, 0.00447, 0.06336, 0.24199, 0.29827, 0.39223, 0.41765, 0.32678, 0.04898, 0.03121, 0.00052, 0.48043, 0.44957, 0.31635, 0.24355, 0.12679, 0.07906, 0.00109, 0.02406, 0.18102, 0.16665, 0.01387, 0.12992, 0.17249, 0.10241, 0.0706, 0.05167, 0.12452, 0.11625, 0.00902, 0.12651, 0.04795, 0.02056, 0.09206, 0.13902, 0.1098, 0.0995, 0.0539, 0.01196, 0.00826, 0.00229, 0.00014, 0.00223, 0.01257, 0.1002 ], "comparison": { "original": "Chance. Oh no, to hear a voice that's very rare. If there is a spirit present, he'll speak to us by tapping with the tape.", "retranscribed": "Chance. Oh no, to hear a voice that's very rare. If there is a spirit present, he'll speak to us by tapping with the tin.", "reference_tokens": [ "chance", "oh", "no", "to", "hear", "a", "voice", "thats", "very", "rare", "if", "there", "is", "a", "spirit", "present", "hell", "speak", "to", "us", "by", "tapping", "with", "the", "tape" ], "hypothesis_tokens": [ "chance", "oh", "no", "to", "hear", "a", "voice", "thats", "very", "rare", "if", "there", "is", "a", "spirit", "present", "hell", "speak", "to", "us", "by", "tapping", "with", "the", "tin" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 24, "reference_words": 25, "hypothesis_words": 25, "edits": 1 }, "wer": 0.04, "wer_percent": 4.0, "alignment": [ { "op": "equal", "reference": "chance", "hypothesis": "chance", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "oh", "hypothesis": "oh", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "hear", "hypothesis": "hear", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "voice", "hypothesis": "voice", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "thats", "hypothesis": "thats", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "very", "hypothesis": "very", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "rare", "hypothesis": "rare", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "if", "hypothesis": "if", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "there", "hypothesis": "there", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "is", "hypothesis": "is", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "spirit", "hypothesis": "spirit", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "present", "hypothesis": "present", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "hell", "hypothesis": "hell", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "speak", "hypothesis": "speak", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "to", "hypothesis": "to", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "us", "hypothesis": "us", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "by", "hypothesis": "by", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "tapping", "hypothesis": "tapping", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "with", "hypothesis": "with", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 23, "hypothesis_index": 23 }, { "op": "substitute", "reference": "tape", "hypothesis": "tin", "reference_index": 24, "hypothesis_index": 24 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.48043, "audio_sample_format": "pcm16" }, { "language": "English", "emotion": "Surprised", "emotion_confidence": 0.7739519476890564, "duration_seconds": 1.7569999999999766, "mos": 3.2976, "audio_variant": "cleaned", "original_transcript_raw": "All the way at the top. ", "original_transcript": "All the way at the top.", "retranscribed_transcript": "All the way at the.", "backend": "qwen", "emotion_analyzed_seconds": 1.757, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-072", "energy": { "value": 0.66015625, "bucket": "high" }, "audio_url": "audio/utterance-072.wav", "spectrogram_url": "spectrograms/utterance-072.png", "waveform": [ 0.4641, 0.48456, 0.37226, 0.24204, 0.1201, 0.11974, 0.2173, 0.1966, 0.22253, 0.20332, 0.16442, 0.15543, 0.24661, 0.22414, 0.21403, 0.26081, 0.28315, 0.30972, 0.31115, 0.33603, 0.33079, 0.33817, 0.41389, 0.41711, 0.41466, 0.41487, 0.41449, 0.39214, 0.39639, 0.35613, 0.32616, 0.31093, 0.30517, 0.31446, 0.28392, 0.26626, 0.21578, 0.18419, 0.15242, 0.13257, 0.12308, 0.12991, 0.11325, 0.11138, 0.10777, 0.15485, 0.19662, 0.35227, 0.36819, 0.38085, 0.38075, 0.30749, 0.27573, 0.224, 0.20588, 0.20953, 0.19068, 0.18602, 0.15202, 0.16445, 0.16903, 0.19472, 0.19926, 0.18859, 0.21084, 0.22013, 0.22674, 0.22505, 0.24896, 0.25438, 0.25917, 0.25612, 0.25307, 0.26139, 0.30641, 0.36071, 0.40532, 0.49075, 0.38591, 0.39281, 0.39996, 0.35808, 0.34227, 0.30388, 0.33326, 0.29426, 0.28679, 0.312, 0.28034, 0.23747, 0.1403, 0.08171, 0.15103, 0.14642, 0.06889, 0.07729, 0.05782, 0.04582, 0.04764, 0.02446, 0.02861, 0.03627, 0.06669, 0.09162, 0.14564, 0.10529, 0.19893, 0.19928, 0.24266, 0.28166, 0.25894, 0.19118, 0.09957, 0.07121, 0.0549, 0.03263, 0.0172, 0.0113, 0.00869, 0.00585, 0.00419, 0.00356, 0.00199, 0.00164, 0.00112, 0.00092, 0.00107, 0.07467, 0.06331, 0.03999, 0.0903, 0.12128, 0.10303, 0.10353, 0.10645, 0.08354, 0.09128, 0.06915, 0.05426, 0.01222, 0.00629, 0.00298, 0.00128, 0.00096, 0.00093, 0.00098, 0.00063, 0.00102, 0.00062, 0.00056, 0.00047, 0.00046, 0.00061, 0.00052, 0.00063, 0.00027, 0.00027, 0.00066, 0.00099, 0.11224, 0.09291, 0.18618, 0.1386, 0.16749, 0.15053, 0.10104, 0.11008, 0.10605, 0.07455, 0.0751, 0.07558, 0.08817, 0.07587, 0.06248, 0.11166, 0.08264, 0.28085, 0.45209, 0.72378, 0.70264 ], "comparison": { "original": "All the way at the top.", "retranscribed": "All the way at the.", "reference_tokens": [ "all", "the", "way", "at", "the", "top" ], "hypothesis_tokens": [ "all", "the", "way", "at", "the" ], "counts": { "substitutions": 0, "deletions": 1, "insertions": 0, "hits": 5, "reference_words": 6, "hypothesis_words": 5, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "equal", "reference": "all", "hypothesis": "all", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "way", "hypothesis": "way", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "at", "hypothesis": "at", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "the", "hypothesis": "the", "reference_index": 4, "hypothesis_index": 4 }, { "op": "delete", "reference": "top", "hypothesis": null, "reference_index": 5, "hypothesis_index": null } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.72378, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Angry", "emotion_confidence": 0.44461509585380554, "duration_seconds": 1.2970000000000255, "mos": 3.1826, "audio_variant": "original", "original_transcript_raw": "Se van de mi propiedad. ", "original_transcript": "Se van de mi propiedad.", "retranscribed_transcript": "Se van de mi propiedad.", "backend": "qwen", "emotion_analyzed_seconds": 1.297, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-073", "energy": { "value": 0.57421875, "bucket": "medium" }, "audio_url": "audio/utterance-073.wav", "spectrogram_url": "spectrograms/utterance-073.png", "waveform": [ 0.00322, 0.00399, 0.00374, 0.0046, 0.00799, 0.01362, 0.01989, 0.06942, 0.0587, 0.0866, 0.12141, 0.13556, 0.14728, 0.14157, 0.15215, 0.1515, 0.08904, 0.14696, 0.13732, 0.11362, 0.25778, 0.1238, 0.15577, 0.07202, 0.07387, 0.0579, 0.0541, 0.09371, 0.12866, 0.16846, 0.22703, 0.19749, 0.29352, 0.39437, 0.49954, 0.52014, 0.48618, 0.5236, 0.32813, 0.43685, 0.4174, 0.22588, 0.41776, 0.26994, 0.21417, 0.31222, 0.2475, 0.24442, 0.25806, 0.26433, 0.26084, 0.26049, 0.25203, 0.23862, 0.22695, 0.37177, 0.43727, 0.56917, 0.55073, 0.43095, 0.51907, 0.39458, 0.18661, 0.2304, 0.25361, 0.24427, 0.23322, 0.23156, 0.25327, 0.33816, 0.35211, 0.17625, 0.4018, 0.3538, 0.27108, 0.27594, 0.21218, 0.09017, 0.0651, 0.06373, 0.02748, 0.02616, 0.01206, 0.0069, 0.00603, 0.00628, 0.03174, 0.05874, 0.13197, 0.33616, 0.15223, 0.20743, 0.35094, 0.2921, 0.59004, 0.65853, 0.35219, 0.30427, 0.06746, 0.10506, 0.06568, 0.04864, 0.03789, 0.01019, 0.00958, 0.00699, 0.00721, 0.03315, 0.06498, 0.07889, 0.1012, 0.22703, 0.19875, 0.26696, 0.24238, 0.21545, 0.25345, 0.21124, 0.18677, 0.21911, 0.29256, 0.21947, 0.17084, 0.15484, 0.09548, 0.07597, 0.13918, 0.141, 0.16906, 0.18488, 0.19591, 0.21099, 0.20217, 0.34923, 0.21717, 0.46183, 0.21339, 0.47842, 0.37779, 0.26592, 0.45506, 0.25307, 0.40106, 0.18119, 0.25795, 0.12857, 0.17486, 0.11616, 0.10691, 0.10548, 0.13626, 0.08763, 0.08336, 0.05833, 0.05342, 0.03957, 0.03713, 0.03291, 0.03312, 0.04227, 0.0299, 0.04378, 0.03502, 0.0468, 0.04828, 0.04759, 0.04211, 0.03867, 0.03915, 0.04038, 0.04394, 0.05569, 0.04381, 0.03385, 0.02867, 0.03167, 0.02534, 0.02472, 0.03097, 0.01433 ], "comparison": { "original": "Se van de mi propiedad.", "retranscribed": "Se van de mi propiedad.", "reference_tokens": [ "se", "van", "de", "mi", "propiedad" ], "hypothesis_tokens": [ "se", "van", "de", "mi", "propiedad" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "se", "hypothesis": "se", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "van", "hypothesis": "van", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "mi", "hypothesis": "mi", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "propiedad", "hypothesis": "propiedad", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.65853, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Angry", "emotion_confidence": 0.3758960962295532, "duration_seconds": 1.3310000000000173, "mos": 3.6396, "audio_variant": "cleaned", "original_transcript_raw": "Intenta proteger", "original_transcript": "Intenta proteger", "retranscribed_transcript": "Intenta protegerlo.", "backend": "qwen", "emotion_analyzed_seconds": 1.331, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-074", "energy": { "value": 0.5546875, "bucket": "medium" }, "audio_url": "audio/utterance-074.wav", "spectrogram_url": "spectrograms/utterance-074.png", "waveform": [ 0.05198, 0.16608, 0.29102, 0.24449, 0.23885, 0.21559, 0.26168, 0.29989, 0.30028, 0.26889, 0.21427, 0.15892, 0.1379, 0.12767, 0.12883, 0.12599, 0.12349, 0.1178, 0.12165, 0.12428, 0.12158, 0.09532, 0.10327, 0.04914, 0.01413, 0.01325, 0.00302, 0.00217, 0.00144, 0.00053, 0.00079, 0.00064, 0.00059, 0.00034, 0.00045, 0.00057, 0.0035, 0.07933, 0.27079, 0.48554, 0.52875, 0.53114, 0.46645, 0.37956, 0.40743, 0.44198, 0.43474, 0.42386, 0.38036, 0.36188, 0.27446, 0.28201, 0.26158, 0.27167, 0.27886, 0.23062, 0.25947, 0.18756, 0.16814, 0.13538, 0.15208, 0.12914, 0.11896, 0.11413, 0.11774, 0.10209, 0.06783, 0.01743, 0.00747, 0.00415, 0.00247, 0.00077, 0.00079, 0.00047, 0.00066, 0.00057, 0.10413, 0.0378, 0.2432, 0.25919, 0.32534, 0.29394, 0.24583, 0.33894, 0.34267, 0.32035, 0.17151, 0.07468, 0.04098, 0.02261, 0.0069, 0.00381, 0.00331, 0.00116, 0.0012, 0.00059, 0.00043, 0.00054, 0.00036, 0.09235, 0.05194, 0.20337, 0.2184, 0.28157, 0.31156, 0.18841, 0.07794, 0.26527, 0.30657, 0.38998, 0.25779, 0.38102, 0.32367, 0.2878, 0.19854, 0.21143, 0.07115, 0.07756, 0.03027, 0.01426, 0.00548, 0.00188, 0.0026, 0.00124, 0.00073, 0.05481, 0.04964, 0.24173, 0.32605, 0.21129, 0.29557, 0.35546, 0.30263, 0.31699, 0.25445, 0.11205, 0.14175, 0.04437, 0.03834, 0.0331, 0.05614, 0.02902, 0.05137, 0.0551, 0.02604, 0.03588, 0.03378, 0.04038, 0.02577, 0.01761, 0.02428, 0.19075, 0.4252, 0.30822, 0.40526, 0.4708, 0.51686, 0.47851, 0.38558, 0.40939, 0.39358, 0.41194, 0.40194, 0.39258, 0.24941, 0.31514, 0.1988, 0.09025, 0.09157, 0.07523, 0.17186, 0.25312, 0.22259, 0.22893, 0.09914, 0.09733, 0.03428, 0.03575, 0.09609, 0.03664 ], "comparison": { "original": "Intenta proteger", "retranscribed": "Intenta protegerlo.", "reference_tokens": [ "intenta", "proteger" ], "hypothesis_tokens": [ "intenta", "protegerlo" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 1, "reference_words": 2, "hypothesis_words": 2, "edits": 1 }, "wer": 0.5, "wer_percent": 50.0, "alignment": [ { "op": "equal", "reference": "intenta", "hypothesis": "intenta", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "proteger", "hypothesis": "protegerlo", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.53114, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Angry", "emotion_confidence": 0.3255881369113922, "duration_seconds": 2.423000000000002, "mos": 3.0334, "audio_variant": "original", "original_transcript_raw": "Quiero cura belga que vivía en Valdivia. ", "original_transcript": "Quiero cura belga que vivía en Valdivia.", "retranscribed_transcript": "tiene un cura belga que vivía en Maldivia", "backend": "qwen", "emotion_analyzed_seconds": 2.423, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-075", "energy": { "value": 0.56640625, "bucket": "medium" }, "audio_url": "audio/utterance-075.wav", "spectrogram_url": "spectrograms/utterance-075.png", "waveform": [ 0.02624, 0.01413, 0.2103, 0.26681, 0.09973, 0.13734, 0.21935, 0.31534, 0.20335, 0.15081, 0.09295, 0.03926, 0.01507, 0.01036, 0.01208, 0.00854, 0.02676, 0.01333, 0.07296, 0.06782, 0.3326, 0.47098, 0.57457, 0.60392, 0.53931, 0.25243, 0.36953, 0.64548, 0.66376, 0.49853, 0.59918, 0.61301, 0.53138, 0.54005, 0.43524, 0.32705, 0.25042, 0.225, 0.27335, 0.29718, 0.42903, 0.49, 0.57963, 0.58339, 0.55805, 0.27302, 0.2738, 0.24982, 0.19789, 0.17074, 0.15255, 0.24621, 0.07105, 0.03819, 0.13274, 0.25597, 0.38658, 0.48895, 0.48731, 0.36931, 0.26945, 0.16425, 0.08286, 0.03407, 0.02041, 0.01357, 0.01308, 0.01004, 0.01449, 0.01115, 0.01117, 0.00988, 0.01065, 0.01902, 0.01139, 0.01153, 0.01457, 0.01534, 0.0108, 0.00948, 0.00891, 0.01299, 0.01102, 0.00966, 0.01041, 0.00887, 0.01229, 0.0149, 0.01503, 0.01234, 0.01104, 0.0111, 0.01206, 0.01047, 0.00766, 0.01012, 0.00808, 0.00971, 0.01177, 0.00684, 0.00955, 0.00629, 0.00848, 0.13548, 0.02655, 0.11927, 0.29138, 0.30523, 0.31774, 0.31565, 0.34277, 0.35326, 0.3573, 0.35943, 0.36563, 0.381, 0.36754, 0.37081, 0.37225, 0.43598, 0.46449, 0.56202, 0.57978, 0.54506, 0.56486, 0.70923, 0.53343, 0.45873, 0.13953, 0.13679, 0.14069, 0.14427, 0.11987, 0.18499, 0.50845, 0.48431, 0.31103, 0.16363, 0.13318, 0.11663, 0.11201, 0.07742, 0.06758, 0.05156, 0.05509, 0.13393, 0.28588, 0.3224, 0.32984, 0.32408, 0.34426, 0.30632, 0.28035, 0.25424, 0.24169, 0.21916, 0.23468, 0.22006, 0.20617, 0.18822, 0.14477, 0.1441, 0.05947, 0.03484, 0.03319, 0.02656, 0.01954, 0.01681, 0.01177, 0.01379, 0.0149, 0.01017, 0.01084, 0.01115, 0.00856, 0.00892, 0.01011, 0.00877, 0.0091, 0.0109 ], "comparison": { "original": "Quiero cura belga que vivía en Valdivia.", "retranscribed": "tiene un cura belga que vivía en Maldivia", "reference_tokens": [ "quiero", "cura", "belga", "que", "vivía", "en", "valdivia" ], "hypothesis_tokens": [ "tiene", "un", "cura", "belga", "que", "vivía", "en", "maldivia" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 1, "hits": 5, "reference_words": 7, "hypothesis_words": 8, "edits": 3 }, "wer": 0.42857142857142855, "wer_percent": 42.857142857142854, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "tiene", "reference_index": null, "hypothesis_index": 0 }, { "op": "substitute", "reference": "quiero", "hypothesis": "un", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "cura", "hypothesis": "cura", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "belga", "hypothesis": "belga", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "vivía", "hypothesis": "vivía", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "en", "hypothesis": "en", "reference_index": 5, "hypothesis_index": 6 }, { "op": "substitute", "reference": "valdivia", "hypothesis": "maldivia", "reference_index": 6, "hypothesis_index": 7 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.70923, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Angry", "emotion_confidence": 0.6306480765342712, "duration_seconds": 1.7239999999999998, "mos": 2.9164, "audio_variant": "cleaned", "original_transcript_raw": "Estoy atorada en el ascensor. ", "original_transcript": "Estoy atorada en el ascensor.", "retranscribed_transcript": "Estoy atorada en el ascensor.", "backend": "qwen", "emotion_analyzed_seconds": 1.724, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-076", "energy": { "value": 0.77734375, "bucket": "high" }, "audio_url": "audio/utterance-076.wav", "spectrogram_url": "spectrograms/utterance-076.png", "waveform": [ 0.10212, 0.04955, 0.03514, 0.01901, 0.01456, 0.03535, 0.06668, 0.08796, 0.08296, 0.10437, 0.14578, 0.13311, 0.03684, 0.05359, 0.05459, 0.05869, 0.07215, 0.04139, 0.02034, 0.00389, 0.00093, 0.00068, 0.00079, 0.0007, 0.06294, 0.29454, 0.29597, 0.25022, 0.19, 0.18016, 0.17509, 0.19425, 0.13763, 0.04863, 0.0561, 0.04861, 0.02463, 0.11655, 0.21329, 0.21049, 0.26686, 0.32121, 0.36726, 0.34908, 0.26711, 0.04933, 0.02176, 0.0044, 0.00216, 0.00072, 0.0006, 0.00044, 0.07701, 0.23573, 0.25843, 0.29386, 0.31461, 0.35602, 0.41472, 0.42105, 0.28384, 0.28655, 0.06637, 0.11034, 0.5051, 0.57126, 0.27388, 0.2799, 0.33469, 0.35842, 0.40222, 0.42806, 0.41188, 0.28944, 0.05536, 0.05119, 0.05396, 0.08025, 0.16802, 0.18043, 0.18265, 0.18305, 0.21398, 0.23192, 0.13781, 0.16748, 0.17287, 0.16729, 0.16078, 0.15093, 0.1449, 0.2469, 0.28252, 0.30587, 0.28032, 0.17901, 0.15916, 0.24589, 0.29032, 0.24087, 0.16884, 0.10102, 0.03437, 0.0175, 0.01917, 0.01998, 0.02729, 0.02949, 0.04406, 0.03668, 0.11745, 0.14569, 0.15664, 0.1789, 0.23784, 0.18636, 0.17324, 0.13014, 0.11991, 0.11615, 0.12854, 0.12807, 0.10279, 0.03657, 0.03524, 0.04332, 0.04953, 0.03754, 0.04008, 0.0274, 0.04336, 0.03109, 0.0349, 0.14055, 0.18614, 0.18319, 0.21837, 0.37496, 0.39402, 0.30392, 0.1893, 0.15283, 0.13424, 0.16204, 0.24397, 0.2678, 0.2202, 0.14106, 0.10685, 0.11087, 0.11912, 0.06777, 0.02962, 0.02685, 0.02032, 0.01782, 0.01601, 0.01444, 0.01158, 0.0096, 0.0065, 0.0033, 0.00265, 0.00175, 0.00059, 0.00101, 0.00103, 0.00137, 0.00234, 0.00311, 0.00218, 0.00272, 0.00503, 0.0033, 0.00282, 0.02028, 0.0257, 0.04209, 0.07362, 0.06277 ], "comparison": { "original": "Estoy atorada en el ascensor.", "retranscribed": "Estoy atorada en el ascensor.", "reference_tokens": [ "estoy", "atorada", "en", "el", "ascensor" ], "hypothesis_tokens": [ "estoy", "atorada", "en", "el", "ascensor" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "estoy", "hypothesis": "estoy", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "atorada", "hypothesis": "atorada", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "en", "hypothesis": "en", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "el", "hypothesis": "el", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "ascensor", "hypothesis": "ascensor", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.57126, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Angry", "emotion_confidence": 0.7474949359893799, "duration_seconds": 8.823000000000036, "mos": 3.4016, "audio_variant": "cleaned", "original_transcript_raw": "Yo quiero que me gasten en mariz, yo quiero que me gasten en pañales. ", "original_transcript": "Yo quiero que me gasten en mariz, yo quiero que me gasten en pañales.", "retranscribed_transcript": "¡No! Yo quiero que me gasten en marín. Yo quiero que me gasten en pañales.", "backend": "qwen", "emotion_analyzed_seconds": 8.823, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-077", "energy": { "value": 0.8359375, "bucket": "high" }, "audio_url": "audio/utterance-077.wav", "spectrogram_url": "spectrograms/utterance-077.png", "waveform": [ 0.22584, 0.24753, 0.18027, 0.09692, 0.1302, 0.02992, 0.01405, 0.01122, 0.01423, 0.00732, 0.00152, 0.00132, 0.00071, 6e-05, 3e-05, 2e-05, 3e-05, 5e-05, 7e-05, 0.00011, 0.0002, 0.00112, 0.00064, 0.00071, 0.00842, 0.00972, 0.01288, 0.10171, 0.19421, 0.29707, 0.05482, 0.11199, 0.06532, 0.04366, 0.02697, 0.00056, 0.00094, 0.13944, 0.45417, 0.47473, 0.05293, 0.04317, 0.33163, 0.31882, 0.39351, 0.44451, 0.46226, 0.03072, 0.22539, 0.41689, 0.24096, 0.20654, 0.17134, 0.15772, 0.1597, 0.35789, 0.28785, 0.00572, 0.22839, 0.27935, 0.10738, 0.17265, 0.17298, 0.09212, 0.08937, 0.39389, 0.42935, 0.39521, 0.24612, 0.23473, 0.29156, 0.29751, 0.29247, 0.26782, 0.22568, 0.18873, 0.17753, 0.1348, 0.00488, 0.00332, 0.00152, 0.02326, 0.06051, 0.28992, 0.39118, 0.2904, 0.06111, 0.14061, 0.26804, 0.19823, 0.30392, 0.22825, 0.10201, 0.37694, 0.12189, 0.42965, 0.44287, 0.03249, 0.11249, 0.19071, 0.30316, 0.04285, 0.01499, 0.43351, 0.31191, 0.28947, 0.32975, 0.17373, 0.03374, 0.41326, 0.27813, 0.30482, 0.12567, 0.22848, 0.41066, 0.37191, 0.62887, 0.57729, 0.23628, 0.30219, 0.38361, 0.13749, 0.21887, 0.17047, 0.03851, 0.01223, 0.00332, 0.00012, 5e-05, 4e-05, 0.00012, 0.0079, 0.02691, 0.03668, 0.03702, 0.03073, 0.01384, 0.02087, 0.01513, 0.01926, 0.01325, 0.02217, 0.06817, 0.04536, 0.04897, 0.06118, 0.0382, 0.0629, 0.03345, 0.02758, 0.01585, 0.01045, 0.00455, 0.00293, 0.00692, 0.00468, 0.00022, 5e-05, 4e-05, 2e-05, 2e-05, 2e-05, 2e-05, 4e-05, 0.00023, 0.02153, 0.39778, 0.33393, 0.34105, 0.23371, 0.2889, 0.22505, 0.1813, 0.21674, 0.20833, 0.17185, 0.03308, 0.0393, 0.06466, 0.0772 ], "comparison": { "original": "Yo quiero que me gasten en mariz, yo quiero que me gasten en pañales.", "retranscribed": "¡No! Yo quiero que me gasten en marín. Yo quiero que me gasten en pañales.", "reference_tokens": [ "yo", "quiero", "que", "me", "gasten", "en", "mariz", "yo", "quiero", "que", "me", "gasten", "en", "pañales" ], "hypothesis_tokens": [ "no", "yo", "quiero", "que", "me", "gasten", "en", "marín", "yo", "quiero", "que", "me", "gasten", "en", "pañales" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 1, "hits": 13, "reference_words": 14, "hypothesis_words": 15, "edits": 2 }, "wer": 0.14285714285714285, "wer_percent": 14.285714285714285, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "no", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "yo", "hypothesis": "yo", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "quiero", "hypothesis": "quiero", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "gasten", "hypothesis": "gasten", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "en", "hypothesis": "en", "reference_index": 5, "hypothesis_index": 6 }, { "op": "substitute", "reference": "mariz", "hypothesis": "marín", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "yo", "hypothesis": "yo", "reference_index": 7, "hypothesis_index": 8 }, { "op": "equal", "reference": "quiero", "hypothesis": "quiero", "reference_index": 8, "hypothesis_index": 9 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 9, "hypothesis_index": 10 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 10, "hypothesis_index": 11 }, { "op": "equal", "reference": "gasten", "hypothesis": "gasten", "reference_index": 11, "hypothesis_index": 12 }, { "op": "equal", "reference": "en", "hypothesis": "en", "reference_index": 12, "hypothesis_index": 13 }, { "op": "equal", "reference": "pañales", "hypothesis": "pañales", "reference_index": 13, "hypothesis_index": 14 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.62887, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Angry", "emotion_confidence": 0.47135087847709656, "duration_seconds": 1.3039999999999985, "mos": 3.0035, "audio_variant": "cleaned", "original_transcript_raw": "La República Democrática del Congo. ", "original_transcript": "La República Democrática del Congo.", "retranscribed_transcript": "La República Democrática del", "backend": "qwen", "emotion_analyzed_seconds": 1.304, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-078", "energy": { "value": 0.62890625, "bucket": "high" }, "audio_url": "audio/utterance-078.wav", "spectrogram_url": "spectrograms/utterance-078.png", "waveform": [ 0.16969, 0.19307, 0.11439, 0.10743, 0.13415, 0.14237, 0.15788, 0.18647, 0.24062, 0.27521, 0.35204, 0.29233, 0.11034, 0.15084, 0.25979, 0.2173, 0.15329, 0.14324, 0.2924, 0.2622, 0.23651, 0.2791, 0.31844, 0.2895, 0.24536, 0.10683, 0.09924, 0.08024, 0.06089, 0.05281, 0.04859, 0.05724, 0.07269, 0.09698, 0.14007, 0.25242, 0.24885, 0.25083, 0.22333, 0.23428, 0.24562, 0.22651, 0.24414, 0.25648, 0.25179, 0.23802, 0.23537, 0.20745, 0.25249, 0.25622, 0.20252, 0.20289, 0.1902, 0.23598, 0.235, 0.23185, 0.24216, 0.24263, 0.27141, 0.22717, 0.1483, 0.06474, 0.05342, 0.0658, 0.20027, 0.26667, 0.31948, 0.27616, 0.28978, 0.31037, 0.37255, 0.32935, 0.3093, 0.31627, 0.31441, 0.31933, 0.36406, 0.37809, 0.27017, 0.13397, 0.16947, 0.17777, 0.17677, 0.16356, 0.16886, 0.16904, 0.2442, 0.24772, 0.24431, 0.25541, 0.26687, 0.24186, 0.24627, 0.24794, 0.10161, 0.06275, 0.05906, 0.0408, 0.04595, 0.08135, 0.09847, 0.16252, 0.20458, 0.24357, 0.16736, 0.05394, 0.1532, 0.45232, 0.44007, 0.32294, 0.30758, 0.33926, 0.33336, 0.2892, 0.26489, 0.16329, 0.05528, 0.053, 0.04609, 0.0445, 0.03849, 0.02975, 0.02604, 0.04512, 0.08532, 0.17886, 0.19284, 0.20374, 0.19501, 0.13839, 0.04273, 0.03009, 0.03797, 0.0601, 0.08531, 0.1725, 0.20563, 0.30234, 0.30493, 0.35342, 0.35784, 0.33728, 0.28746, 0.26197, 0.21727, 0.16147, 0.17131, 0.16227, 0.18692, 0.1866, 0.21664, 0.22502, 0.20382, 0.22936, 0.23514, 0.19565, 0.20151, 0.23074, 0.23067, 0.22257, 0.20131, 0.18993, 0.19406, 0.15502, 0.0922, 0.03973, 0.03076, 0.0161, 0.00515, 0.00282, 0.03283, 0.10543, 0.07739, 0.13851, 0.17086, 0.26886, 0.28768, 0.29111, 0.30299, 0.31334 ], "comparison": { "original": "La República Democrática del Congo.", "retranscribed": "La República Democrática del", "reference_tokens": [ "la", "república", "democrática", "del", "congo" ], "hypothesis_tokens": [ "la", "república", "democrática", "del" ], "counts": { "substitutions": 0, "deletions": 1, "insertions": 0, "hits": 4, "reference_words": 5, "hypothesis_words": 4, "edits": 1 }, "wer": 0.2, "wer_percent": 20.0, "alignment": [ { "op": "equal", "reference": "la", "hypothesis": "la", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "república", "hypothesis": "república", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "democrática", "hypothesis": "democrática", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "del", "hypothesis": "del", "reference_index": 3, "hypothesis_index": 3 }, { "op": "delete", "reference": "congo", "hypothesis": null, "reference_index": 4, "hypothesis_index": null } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.45232, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Annoyed", "emotion_confidence": 0.5888650417327881, "duration_seconds": 6.048999999999978, "mos": 3.51, "audio_variant": "cleaned", "original_transcript_raw": "El que yo pudiera hacer cosas sin estarle pidiendo, eh", "original_transcript": "El que yo pudiera hacer cosas sin estarle pidiendo, eh", "retranscribed_transcript": "El que yo pudiera hacer cosas sin estarle pidiendo", "backend": "qwen", "emotion_analyzed_seconds": 6.049, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-079", "energy": { "value": 0.494140625, "bucket": "low" }, "audio_url": "audio/utterance-079.wav", "spectrogram_url": "spectrograms/utterance-079.png", "waveform": [ 0.03394, 0.01014, 0.2579, 0.55466, 0.37436, 0.29162, 0.05381, 0.04079, 0.3235, 0.41086, 0.35653, 0.15787, 0.09871, 0.54638, 0.55738, 0.34737, 0.0818, 0.00269, 0.01122, 0.32748, 0.31061, 0.30211, 0.13403, 0.20702, 0.28959, 0.35257, 0.36013, 0.22219, 0.46467, 0.39528, 0.34608, 0.16046, 0.0466, 0.03509, 0.18264, 0.3096, 0.30938, 0.15399, 0.23688, 0.042, 0.00223, 0.00123, 0.00119, 0.01959, 0.0815, 0.35691, 0.35484, 0.23538, 0.24477, 0.05602, 0.05724, 0.03127, 0.2488, 0.28953, 0.15327, 0.0462, 0.03772, 0.03624, 0.02014, 0.0018, 0.00428, 0.01013, 0.01007, 0.00876, 0.00935, 0.00719, 0.00519, 0.00244, 0.00099, 0.01602, 0.02369, 0.02925, 0.02868, 0.34087, 0.31628, 0.30527, 0.27201, 0.28383, 0.35838, 0.33542, 0.31882, 0.18191, 0.0513, 0.0278, 0.01599, 0.00082, 0.04818, 0.38025, 0.44699, 0.42652, 0.42105, 0.1575, 0.07611, 0.22943, 0.24858, 0.24239, 0.27925, 0.26886, 0.21588, 0.2079, 0.22317, 0.2197, 0.26008, 0.25668, 0.23341, 0.22909, 0.19908, 0.05632, 0.00737, 0.00415, 0.00503, 0.00461, 0.00508, 0.00561, 0.00757, 0.00707, 0.00875, 0.0064, 0.00547, 0.00318, 0.00235, 0.00078, 0.00077, 0.00061, 0.00052, 0.41976, 0.41434, 0.33137, 0.28055, 0.15306, 0.14382, 0.38792, 0.36535, 0.46237, 0.42471, 0.5259, 0.43542, 0.43462, 0.27788, 0.26417, 0.2695, 0.11073, 0.42678, 0.41665, 0.23456, 0.14336, 0.06751, 0.0064, 0.00285, 0.0013, 0.00091, 0.00074, 0.00041, 0.00074, 0.00059, 0.0007, 0.00056, 0.00069, 0.0008, 0.17984, 0.17221, 0.18135, 0.15889, 0.1563, 0.1612, 0.16726, 0.16612, 0.16935, 0.16938, 0.19806, 0.17251, 0.18924, 0.17986, 0.18654, 0.14637, 0.1551, 0.12254, 0.0619, 0.04532, 0.03701 ], "comparison": { "original": "El que yo pudiera hacer cosas sin estarle pidiendo, eh", "retranscribed": "El que yo pudiera hacer cosas sin estarle pidiendo", "reference_tokens": [ "el", "que", "yo", "pudiera", "hacer", "cosas", "sin", "estarle", "pidiendo", "eh" ], "hypothesis_tokens": [ "el", "que", "yo", "pudiera", "hacer", "cosas", "sin", "estarle", "pidiendo" ], "counts": { "substitutions": 0, "deletions": 1, "insertions": 0, "hits": 9, "reference_words": 10, "hypothesis_words": 9, "edits": 1 }, "wer": 0.1, "wer_percent": 10.0, "alignment": [ { "op": "equal", "reference": "el", "hypothesis": "el", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "yo", "hypothesis": "yo", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "pudiera", "hypothesis": "pudiera", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "hacer", "hypothesis": "hacer", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "cosas", "hypothesis": "cosas", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "sin", "hypothesis": "sin", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "estarle", "hypothesis": "estarle", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "pidiendo", "hypothesis": "pidiendo", "reference_index": 8, "hypothesis_index": 8 }, { "op": "delete", "reference": "eh", "hypothesis": null, "reference_index": 9, "hypothesis_index": null } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.55738, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Annoyed", "emotion_confidence": 0.49654409289360046, "duration_seconds": 2.2689999999999984, "mos": 3.3333, "audio_variant": "cleaned", "original_transcript_raw": "Estoy segura. ", "original_transcript": "Estoy segura.", "retranscribed_transcript": "Estoy segura.", "backend": "qwen", "emotion_analyzed_seconds": 2.269, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-080", "energy": { "value": 0.4140625, "bucket": "low" }, "audio_url": "audio/utterance-080.wav", "spectrogram_url": "spectrograms/utterance-080.png", "waveform": [ 0.02465, 0.01984, 0.02104, 0.01005, 0.1329, 0.34395, 0.37219, 0.37979, 0.24104, 0.18886, 0.13338, 0.09564, 0.10076, 0.11963, 0.13294, 0.16628, 0.15911, 0.142, 0.09572, 0.08145, 0.03855, 0.0105, 0.0018, 0.00145, 0.00104, 0.00169, 0.08221, 0.29611, 0.50114, 0.51572, 0.49954, 0.52775, 0.48638, 0.41721, 0.39842, 0.39259, 0.37818, 0.34995, 0.35157, 0.35149, 0.37114, 0.41276, 0.3987, 0.32845, 0.30633, 0.33103, 0.31306, 0.26117, 0.24916, 0.25251, 0.22123, 0.19852, 0.18076, 0.14814, 0.16136, 0.11907, 0.13297, 0.135, 0.13444, 0.13129, 0.12351, 0.11137, 0.06645, 0.06657, 0.07156, 0.06883, 0.11296, 0.08155, 0.10349, 0.08633, 0.07721, 0.07767, 0.06504, 0.08038, 0.06456, 0.058, 0.06164, 0.06959, 0.03949, 0.03602, 0.03983, 0.03642, 0.03334, 0.02842, 0.03375, 0.02343, 0.01833, 0.01279, 0.01057, 0.01013, 0.00646, 0.00309, 0.00167, 0.00134, 0.00118, 0.00141, 0.00148, 0.00127, 0.0013, 0.00077, 0.0011, 0.00125, 0.00127, 0.001, 0.00186, 0.00122, 0.00132, 0.00061, 0.00074, 0.00082, 0.00127, 0.00107, 0.00071, 0.00075, 0.00084, 0.00079, 0.00061, 0.00079, 0.00077, 0.001, 0.00161, 0.00403, 0.01481, 0.04935, 0.0472, 0.04895, 0.05031, 0.04383, 0.07041, 0.25542, 0.41589, 0.42376, 0.43171, 0.44672, 0.4204, 0.32603, 0.2047, 0.08089, 0.0542, 0.04144, 0.08219, 0.11868, 0.21236, 0.20348, 0.24967, 0.23254, 0.25734, 0.27196, 0.30329, 0.28894, 0.31458, 0.1994, 0.06863, 0.07465, 0.13466, 0.24947, 0.25388, 0.19045, 0.22459, 0.20216, 0.18634, 0.13048, 0.14134, 0.10775, 0.15826, 0.10583, 0.09697, 0.07272, 0.07661, 0.06026, 0.04391, 0.02575, 0.01844, 0.01186, 0.00592, 0.0038, 0.00799, 0.02972, 0.02565, 0.04876 ], "comparison": { "original": "Estoy segura.", "retranscribed": "Estoy segura.", "reference_tokens": [ "estoy", "segura" ], "hypothesis_tokens": [ "estoy", "segura" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 2, "hypothesis_words": 2, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "estoy", "hypothesis": "estoy", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "segura", "hypothesis": "segura", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.52775, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Annoyed", "emotion_confidence": 0.5955737829208374, "duration_seconds": 3.1910000000000025, "mos": 2.805, "audio_variant": "cleaned", "original_transcript_raw": "Natalia, tú sabes que esto no es tu culpa, verdad? ", "original_transcript": "Natalia, tú sabes que esto no es tu culpa, verdad?", "retranscribed_transcript": "Natalia, tú sabes que esto no es tu culpa, ¿verdad?", "backend": "qwen", "emotion_analyzed_seconds": 3.191, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-081", "energy": { "value": 0.515625, "bucket": "low" }, "audio_url": "audio/utterance-081.wav", "spectrogram_url": "spectrograms/utterance-081.png", "waveform": [ 0.15916, 0.24088, 0.32813, 0.33801, 0.32976, 0.22584, 0.13019, 0.03176, 0.00227, 0.00186, 0.20856, 0.48261, 0.42745, 0.39603, 0.2154, 0.16289, 0.18035, 0.20775, 0.35306, 0.37781, 0.40885, 0.34582, 0.48726, 0.49023, 0.49858, 0.43143, 0.40704, 0.36764, 0.33583, 0.29236, 0.20472, 0.04617, 0.00242, 0.002, 0.00089, 0.00077, 0.00065, 0.0007, 0.00076, 0.00057, 0.00064, 0.00066, 0.00073, 0.0006, 0.00079, 0.00071, 0.001, 0.00069, 0.00081, 0.00075, 0.0009, 0.00081, 0.00111, 0.00091, 0.00096, 0.00088, 0.00111, 0.00151, 0.00085, 0.00119, 0.00126, 0.00098, 0.00142, 0.00148, 0.00101, 0.00107, 0.00118, 0.0011, 0.00135, 0.00139, 0.00086, 0.0019, 0.03067, 0.03954, 0.18449, 0.21149, 0.18828, 0.12397, 0.1043, 0.1301, 0.16139, 0.08113, 0.34494, 0.42399, 0.5588, 0.5299, 0.44107, 0.49382, 0.54574, 0.55951, 0.39368, 0.19944, 0.14494, 0.04432, 0.00365, 0.00245, 0.0536, 0.05795, 0.36342, 0.35436, 0.23365, 0.13678, 0.09195, 0.00488, 0.00213, 0.00163, 0.06039, 0.15853, 0.43121, 0.37392, 0.37754, 0.25769, 0.26222, 0.2791, 0.30734, 0.39323, 0.36225, 0.37716, 0.36602, 0.21915, 0.07102, 0.0176, 0.00359, 0.00126, 0.0416, 0.09295, 0.29271, 0.29732, 0.16546, 0.06608, 0.00458, 0.02842, 0.11169, 0.08349, 0.28764, 0.36979, 0.43438, 0.42151, 0.42349, 0.38957, 0.1325, 0.00576, 0.00285, 0.00715, 0.3399, 0.29968, 0.24801, 0.27005, 0.28737, 0.22754, 0.29044, 0.3169, 0.34891, 0.35966, 0.20371, 0.29468, 0.24937, 0.22082, 0.27596, 0.31804, 0.33365, 0.2818, 0.26227, 0.2781, 0.22979, 0.22843, 0.12453, 0.0686, 0.02871, 0.01204, 0.00956, 0.0112, 0.00771, 0.00912, 0.00701, 0.00445, 0.00516, 0.00762, 0.01466, 0.02711 ], "comparison": { "original": "Natalia, tú sabes que esto no es tu culpa, verdad?", "retranscribed": "Natalia, tú sabes que esto no es tu culpa, ¿verdad?", "reference_tokens": [ "natalia", "tú", "sabes", "que", "esto", "no", "es", "tu", "culpa", "verdad" ], "hypothesis_tokens": [ "natalia", "tú", "sabes", "que", "esto", "no", "es", "tu", "culpa", "verdad" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 10, "reference_words": 10, "hypothesis_words": 10, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "natalia", "hypothesis": "natalia", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "tú", "hypothesis": "tú", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "sabes", "hypothesis": "sabes", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "esto", "hypothesis": "esto", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "es", "hypothesis": "es", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "tu", "hypothesis": "tu", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "culpa", "hypothesis": "culpa", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "verdad", "hypothesis": "verdad", "reference_index": 9, "hypothesis_index": 9 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.55951, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Annoyed", "emotion_confidence": 0.38185539841651917, "duration_seconds": 2.5260000000000105, "mos": 3.5127, "audio_variant": "cleaned", "original_transcript_raw": "Viendo muchas facetas tuyas y está bien. ", "original_transcript": "Viendo muchas facetas tuyas y está bien.", "retranscribed_transcript": "Estoy viendo muchas facetas tuyas y ya está bien.", "backend": "qwen", "emotion_analyzed_seconds": 2.526, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-082", "energy": { "value": 0.57421875, "bucket": "medium" }, "audio_url": "audio/utterance-082.wav", "spectrogram_url": "spectrograms/utterance-082.png", "waveform": [ 0.02718, 0.0959, 0.20874, 0.27426, 0.19455, 0.15349, 0.1106, 0.0554, 0.02318, 0.0261, 0.06415, 0.23471, 0.45919, 0.37664, 0.42079, 0.39418, 0.26534, 0.21221, 0.21168, 0.27443, 0.39474, 0.41332, 0.46634, 0.46505, 0.43257, 0.42155, 0.22906, 0.27356, 0.2333, 0.15883, 0.12616, 0.11822, 0.33684, 0.44459, 0.44596, 0.45016, 0.38145, 0.39581, 0.38024, 0.37087, 0.34174, 0.33506, 0.34756, 0.34958, 0.33609, 0.33251, 0.36154, 0.3717, 0.39343, 0.3573, 0.26886, 0.17196, 0.05941, 0.04282, 0.07375, 0.11902, 0.10369, 0.26297, 0.36483, 0.34165, 0.28457, 0.16823, 0.0653, 0.05932, 0.072, 0.05596, 0.01823, 0.01491, 0.03155, 0.1713, 0.35762, 0.37369, 0.33062, 0.14983, 0.06894, 0.06166, 0.06423, 0.06029, 0.17904, 0.243, 0.21823, 0.1965, 0.08642, 0.03574, 0.00892, 0.00285, 0.03701, 0.21064, 0.2646, 0.2139, 0.13891, 0.09504, 0.04021, 0.01715, 0.00348, 0.00168, 0.00087, 0.00378, 0.11442, 0.25068, 0.23461, 0.22675, 0.25663, 0.25326, 0.18943, 0.17481, 0.12458, 0.15028, 0.17588, 0.2073, 0.21302, 0.20365, 0.11458, 0.06628, 0.03801, 0.05591, 0.01288, 0.00243, 0.00162, 0.00134, 0.00101, 0.00071, 0.08061, 0.23037, 0.24258, 0.25172, 0.20471, 0.21548, 0.30013, 0.35924, 0.27094, 0.34533, 0.20698, 0.13236, 0.08706, 0.09844, 0.01498, 0.02225, 0.03237, 0.19146, 0.39221, 0.43177, 0.43557, 0.28558, 0.29426, 0.36228, 0.40922, 0.33518, 0.39276, 0.27848, 0.27869, 0.27067, 0.25951, 0.23326, 0.15044, 0.09022, 0.02412, 0.00751, 0.00308, 0.00217, 0.00143, 0.00118, 0.00083, 0.00052, 0.00046, 0.00036, 0.00018, 0.00031, 0.00035, 0.00035, 0.00031, 0.00031, 0.00029, 0.0003, 0.00025, 0.00023, 0.00132, 0.00259, 0.00582, 0.00796 ], "comparison": { "original": "Viendo muchas facetas tuyas y está bien.", "retranscribed": "Estoy viendo muchas facetas tuyas y ya está bien.", "reference_tokens": [ "viendo", "muchas", "facetas", "tuyas", "y", "está", "bien" ], "hypothesis_tokens": [ "estoy", "viendo", "muchas", "facetas", "tuyas", "y", "ya", "está", "bien" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 2, "hits": 7, "reference_words": 7, "hypothesis_words": 9, "edits": 2 }, "wer": 0.2857142857142857, "wer_percent": 28.57142857142857, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "estoy", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "viendo", "hypothesis": "viendo", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "muchas", "hypothesis": "muchas", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "facetas", "hypothesis": "facetas", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "tuyas", "hypothesis": "tuyas", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 4, "hypothesis_index": 5 }, { "op": "insert", "reference": null, "hypothesis": "ya", "reference_index": null, "hypothesis_index": 6 }, { "op": "equal", "reference": "está", "hypothesis": "está", "reference_index": 5, "hypothesis_index": 7 }, { "op": "equal", "reference": "bien", "hypothesis": "bien", "reference_index": 6, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.46634, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Annoyed", "emotion_confidence": 0.3703485429286957, "duration_seconds": 5.273000000000025, "mos": 3.6155, "audio_variant": "original", "original_transcript_raw": "Sentía celoso y a veces yo explotaba de niño con ella. ", "original_transcript": "Sentía celoso y a veces yo explotaba de niño con ella.", "retranscribed_transcript": "Te sentía celoso. Te me sentía celoso y a veces yo explotaba de niño con ella.", "backend": "qwen", "emotion_analyzed_seconds": 5.273, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-083", "energy": { "value": 0.55078125, "bucket": "medium" }, "audio_url": "audio/utterance-083.wav", "spectrogram_url": "spectrograms/utterance-083.png", "waveform": [ 0.13187, 0.12916, 0.09814, 0.08186, 0.13902, 0.11197, 0.09418, 0.03264, 0.17176, 0.19402, 0.08208, 0.05193, 0.04516, 0.12864, 0.15687, 0.10605, 0.08803, 0.07804, 0.13257, 0.12279, 0.10415, 0.06501, 0.06393, 0.05626, 0.04267, 0.01737, 0.02813, 0.00554, 0.00148, 0.04271, 0.10973, 0.11404, 0.06836, 0.08858, 0.09768, 0.11793, 0.12038, 0.14119, 0.11203, 0.09029, 0.09277, 0.09, 0.05814, 0.02435, 0.1, 0.13724, 0.14791, 0.16044, 0.18867, 0.14598, 0.15909, 0.17352, 0.12721, 0.04989, 0.14794, 0.11202, 0.12718, 0.13291, 0.13337, 0.11408, 0.08854, 0.06735, 0.09972, 0.11222, 0.0744, 0.08334, 0.05736, 0.03993, 0.02538, 0.02132, 0.01855, 0.00986, 0.00695, 0.03071, 0.02318, 0.03485, 0.05926, 0.09778, 0.12518, 0.09472, 0.09138, 0.10439, 0.11823, 0.12069, 0.09374, 0.14196, 0.09022, 0.11928, 0.11982, 0.1593, 0.16893, 0.1348, 0.13136, 0.13218, 0.04183, 0.09022, 0.12154, 0.1152, 0.11741, 0.11965, 0.11392, 0.088, 0.03987, 0.00783, 0.04912, 0.06925, 0.09205, 0.02358, 0.13969, 0.09344, 0.00765, 0.00971, 0.09635, 0.11408, 0.09603, 0.092, 0.03741, 0.00151, 0.0728, 0.14897, 0.13857, 0.16307, 0.15174, 0.12844, 0.12668, 0.12207, 0.11095, 0.10638, 0.08525, 0.06178, 0.09364, 0.10393, 0.10409, 0.1064, 0.0993, 0.09741, 0.09261, 0.09639, 0.03387, 0.00246, 0.10764, 0.09399, 0.09282, 0.07598, 0.10192, 0.12062, 0.1217, 0.12398, 0.11599, 0.07773, 0.06818, 0.06312, 0.08103, 0.10051, 0.09046, 0.07884, 0.08325, 0.10176, 0.07848, 0.07728, 0.06366, 0.03382, 0.00493, 0.00601, 0.02121, 0.02514, 0.02335, 0.0292, 0.02119, 0.02815, 0.02373, 0.02786, 0.02927, 0.02317, 0.01135, 0.00756, 0.00139, 0.00041, 0.00033, 0.06305 ], "comparison": { "original": "Sentía celoso y a veces yo explotaba de niño con ella.", "retranscribed": "Te sentía celoso. Te me sentía celoso y a veces yo explotaba de niño con ella.", "reference_tokens": [ "sentía", "celoso", "y", "a", "veces", "yo", "explotaba", "de", "niño", "con", "ella" ], "hypothesis_tokens": [ "te", "sentía", "celoso", "te", "me", "sentía", "celoso", "y", "a", "veces", "yo", "explotaba", "de", "niño", "con", "ella" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 5, "hits": 11, "reference_words": 11, "hypothesis_words": 16, "edits": 5 }, "wer": 0.45454545454545453, "wer_percent": 45.45454545454545, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "te", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "sentía", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "celoso", "reference_index": null, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "te", "reference_index": null, "hypothesis_index": 3 }, { "op": "insert", "reference": null, "hypothesis": "me", "reference_index": null, "hypothesis_index": 4 }, { "op": "equal", "reference": "sentía", "hypothesis": "sentía", "reference_index": 0, "hypothesis_index": 5 }, { "op": "equal", "reference": "celoso", "hypothesis": "celoso", "reference_index": 1, "hypothesis_index": 6 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 2, "hypothesis_index": 7 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 3, "hypothesis_index": 8 }, { "op": "equal", "reference": "veces", "hypothesis": "veces", "reference_index": 4, "hypothesis_index": 9 }, { "op": "equal", "reference": "yo", "hypothesis": "yo", "reference_index": 5, "hypothesis_index": 10 }, { "op": "equal", "reference": "explotaba", "hypothesis": "explotaba", "reference_index": 6, "hypothesis_index": 11 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 7, "hypothesis_index": 12 }, { "op": "equal", "reference": "niño", "hypothesis": "niño", "reference_index": 8, "hypothesis_index": 13 }, { "op": "equal", "reference": "con", "hypothesis": "con", "reference_index": 9, "hypothesis_index": 14 }, { "op": "equal", "reference": "ella", "hypothesis": "ella", "reference_index": 10, "hypothesis_index": 15 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.19402, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Annoyed", "emotion_confidence": 0.7567101120948792, "duration_seconds": 4.4709999999999965, "mos": 3.1002, "audio_variant": "original", "original_transcript_raw": "Sólo que por la inflación tendré que cobrar una leve cuota por mis servicios. ", "original_transcript": "Sólo que por la inflación tendré que cobrar una leve cuota por mis servicios.", "retranscribed_transcript": "Solo que por la inflación tendré que cobrar una leve cuota por mis servicios.", "backend": "qwen", "emotion_analyzed_seconds": 4.471, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-084", "energy": { "value": 0.5546875, "bucket": "medium" }, "audio_url": "audio/utterance-084.wav", "spectrogram_url": "spectrograms/utterance-084.png", "waveform": [ 0.01004, 0.00457, 0.03872, 0.08998, 0.10834, 0.21196, 0.34925, 0.24386, 0.21935, 0.12271, 0.18033, 0.27262, 0.21939, 0.17882, 0.14408, 0.06048, 0.01888, 0.24776, 0.37343, 0.3773, 0.34762, 0.29169, 0.17736, 0.08778, 0.04784, 0.11122, 0.39821, 0.35529, 0.36258, 0.3148, 0.13421, 0.17832, 0.38557, 0.42031, 0.3558, 0.2904, 0.14196, 0.11662, 0.05708, 0.03583, 0.0364, 0.23756, 0.41653, 0.39318, 0.33376, 0.28967, 0.12159, 0.05346, 0.06899, 0.12439, 0.08213, 0.06123, 0.28562, 0.29834, 0.33573, 0.36658, 0.3632, 0.32384, 0.21392, 0.21752, 0.10667, 0.13338, 0.10104, 0.04321, 0.02905, 0.22195, 0.58049, 0.28248, 0.2417, 0.13102, 0.14448, 0.07146, 0.34885, 0.19983, 0.28246, 0.27361, 0.07828, 0.03417, 0.12602, 0.5651, 0.48366, 0.09758, 0.04014, 0.03158, 0.26999, 0.39352, 0.16811, 0.10094, 0.19617, 0.3773, 0.3346, 0.30364, 0.27756, 0.12197, 0.15801, 0.17877, 0.21564, 0.20122, 0.13013, 0.15568, 0.38622, 0.34249, 0.26479, 0.19768, 0.20642, 0.2684, 0.32031, 0.25448, 0.24723, 0.16046, 0.10942, 0.26282, 0.22798, 0.24319, 0.07885, 0.04394, 0.02389, 0.01744, 0.05953, 0.29821, 0.34442, 0.3537, 0.22157, 0.27999, 0.26313, 0.22627, 0.05176, 0.03723, 0.02506, 0.05868, 0.47137, 0.28233, 0.27445, 0.11085, 0.04417, 0.03721, 0.01853, 0.16205, 0.39708, 0.32051, 0.23371, 0.07041, 0.124, 0.13662, 0.14497, 0.18938, 0.20079, 0.03764, 0.07071, 0.07674, 0.20399, 0.48196, 0.21798, 0.08269, 0.10732, 0.09941, 0.08316, 0.19584, 0.19636, 0.17055, 0.129, 0.06186, 0.03622, 0.05121, 0.04601, 0.1322, 0.19555, 0.16074, 0.09774, 0.06334, 0.03327, 0.02945, 0.02731, 0.0296, 0.02743, 0.01377, 0.01012, 0.01028, 0.00984, 0.01116 ], "comparison": { "original": "Sólo que por la inflación tendré que cobrar una leve cuota por mis servicios.", "retranscribed": "Solo que por la inflación tendré que cobrar una leve cuota por mis servicios.", "reference_tokens": [ "sólo", "que", "por", "la", "inflación", "tendré", "que", "cobrar", "una", "leve", "cuota", "por", "mis", "servicios" ], "hypothesis_tokens": [ "solo", "que", "por", "la", "inflación", "tendré", "que", "cobrar", "una", "leve", "cuota", "por", "mis", "servicios" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 13, "reference_words": 14, "hypothesis_words": 14, "edits": 1 }, "wer": 0.07142857142857142, "wer_percent": 7.142857142857142, "alignment": [ { "op": "substitute", "reference": "sólo", "hypothesis": "solo", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "por", "hypothesis": "por", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "la", "hypothesis": "la", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "inflación", "hypothesis": "inflación", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "tendré", "hypothesis": "tendré", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "cobrar", "hypothesis": "cobrar", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "una", "hypothesis": "una", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "leve", "hypothesis": "leve", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "cuota", "hypothesis": "cuota", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "por", "hypothesis": "por", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "mis", "hypothesis": "mis", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "servicios", "hypothesis": "servicios", "reference_index": 13, "hypothesis_index": 13 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.58049, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Annoyed", "emotion_confidence": 0.44858694076538086, "duration_seconds": 6.946, "mos": 3.3135, "audio_variant": "cleaned", "original_transcript_raw": "Resistimos todos juntos haz lo que quieras, pero no metas a mi hija en eso. Me parece que Gertrud ya puede si es igual de tonta que tú. ", "original_transcript": "Resistimos todos juntos haz lo que quieras, pero no metas a mi hija en eso. Me parece que Gertrud ya puede si es igual de tonta que tú.", "retranscribed_transcript": "Si resistimos todos juntos. No hagas lo que quieras, pero no metas a mi hija en esto. Me parece que Gertrud ya puede decidir. No si es igual de tonta que tú.", "backend": "qwen", "emotion_analyzed_seconds": 6.946, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-085", "energy": { "value": 0.70703125, "bucket": "high" }, "audio_url": "audio/utterance-085.wav", "spectrogram_url": "spectrograms/utterance-085.png", "waveform": [ 0.2557, 0.37375, 0.26662, 0.1075, 0.37944, 0.40642, 0.32879, 0.08762, 0.18025, 0.19035, 0.10941, 0.01676, 0.23867, 0.37921, 0.35249, 0.13602, 0.38773, 0.51852, 0.18734, 0.07342, 0.26497, 0.52178, 0.38113, 0.2303, 0.4394, 0.30356, 0.07915, 0.0339, 0.36249, 0.37868, 0.24578, 0.0892, 0.55926, 0.45498, 0.2492, 0.15879, 0.06116, 0.60311, 0.58471, 0.44591, 0.17897, 0.03057, 0.11209, 0.16997, 0.53353, 0.54787, 0.00352, 0.22383, 0.3771, 0.05108, 0.07072, 0.12334, 0.27115, 0.19407, 0.11462, 0.21399, 0.05841, 0.02138, 0.00096, 0.37882, 0.29163, 0.25108, 0.22245, 0.09845, 0.31055, 0.28547, 0.08336, 0.25864, 0.22368, 0.27763, 0.00365, 0.33786, 0.30202, 0.03546, 0.1664, 0.32274, 0.2171, 0.22214, 0.23338, 0.21393, 0.23489, 0.08901, 0.0329, 0.3349, 0.15672, 0.09545, 0.1748, 0.19483, 0.20773, 0.03525, 0.02452, 0.07698, 0.21793, 0.26136, 0.03125, 0.39115, 0.58727, 0.32678, 0.36338, 0.2473, 0.24277, 0.07368, 0.22581, 0.26685, 0.0652, 0.17142, 0.31613, 0.24889, 0.14101, 0.63845, 0.67174, 0.3383, 0.25642, 0.03073, 0.27184, 0.34657, 0.17753, 0.02979, 0.16416, 0.42284, 0.56441, 0.04953, 0.22559, 0.44762, 0.30428, 0.31434, 0.25654, 0.15371, 0.13501, 0.17286, 0.06207, 0.10742, 0.19889, 0.19922, 0.30773, 0.239, 0.18471, 0.29797, 0.23325, 0.04779, 0.02642, 0.20313, 0.1708, 0.28809, 0.22613, 0.02222, 0.21534, 0.25142, 0.05378, 0.12742, 0.50816, 0.27456, 0.19533, 0.09536, 0.09009, 0.33218, 0.20709, 0.00472, 0.22554, 0.28732, 0.21468, 0.0931, 0.06728, 0.14861, 0.35784, 0.02451, 0.00062, 0.07058, 0.06281, 0.00293, 0.00039, 0.18431, 0.1568, 0.10235, 0.10439, 0.04056, 0.00263, 4e-05, 0.00378, 0.01361 ], "comparison": { "original": "Resistimos todos juntos haz lo que quieras, pero no metas a mi hija en eso. Me parece que Gertrud ya puede si es igual de tonta que tú.", "retranscribed": "Si resistimos todos juntos. No hagas lo que quieras, pero no metas a mi hija en esto. Me parece que Gertrud ya puede decidir. No si es igual de tonta que tú.", "reference_tokens": [ "resistimos", "todos", "juntos", "haz", "lo", "que", "quieras", "pero", "no", "metas", "a", "mi", "hija", "en", "eso", "me", "parece", "que", "gertrud", "ya", "puede", "si", "es", "igual", "de", "tonta", "que", "tú" ], "hypothesis_tokens": [ "si", "resistimos", "todos", "juntos", "no", "hagas", "lo", "que", "quieras", "pero", "no", "metas", "a", "mi", "hija", "en", "esto", "me", "parece", "que", "gertrud", "ya", "puede", "decidir", "no", "si", "es", "igual", "de", "tonta", "que", "tú" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 4, "hits": 26, "reference_words": 28, "hypothesis_words": 32, "edits": 6 }, "wer": 0.21428571428571427, "wer_percent": 21.428571428571427, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "si", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "resistimos", "hypothesis": "resistimos", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "todos", "hypothesis": "todos", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "juntos", "hypothesis": "juntos", "reference_index": 2, "hypothesis_index": 3 }, { "op": "insert", "reference": null, "hypothesis": "no", "reference_index": null, "hypothesis_index": 4 }, { "op": "substitute", "reference": "haz", "hypothesis": "hagas", "reference_index": 3, "hypothesis_index": 5 }, { "op": "equal", "reference": "lo", "hypothesis": "lo", "reference_index": 4, "hypothesis_index": 6 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 5, "hypothesis_index": 7 }, { "op": "equal", "reference": "quieras", "hypothesis": "quieras", "reference_index": 6, "hypothesis_index": 8 }, { "op": "equal", "reference": "pero", "hypothesis": "pero", "reference_index": 7, "hypothesis_index": 9 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 8, "hypothesis_index": 10 }, { "op": "equal", "reference": "metas", "hypothesis": "metas", "reference_index": 9, "hypothesis_index": 11 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 10, "hypothesis_index": 12 }, { "op": "equal", "reference": "mi", "hypothesis": "mi", "reference_index": 11, "hypothesis_index": 13 }, { "op": "equal", "reference": "hija", "hypothesis": "hija", "reference_index": 12, "hypothesis_index": 14 }, { "op": "equal", "reference": "en", "hypothesis": "en", "reference_index": 13, "hypothesis_index": 15 }, { "op": "substitute", "reference": "eso", "hypothesis": "esto", "reference_index": 14, "hypothesis_index": 16 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 15, "hypothesis_index": 17 }, { "op": "equal", "reference": "parece", "hypothesis": "parece", "reference_index": 16, "hypothesis_index": 18 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 17, "hypothesis_index": 19 }, { "op": "equal", "reference": "gertrud", "hypothesis": "gertrud", "reference_index": 18, "hypothesis_index": 20 }, { "op": "equal", "reference": "ya", "hypothesis": "ya", "reference_index": 19, "hypothesis_index": 21 }, { "op": "equal", "reference": "puede", "hypothesis": "puede", "reference_index": 20, "hypothesis_index": 22 }, { "op": "insert", "reference": null, "hypothesis": "decidir", "reference_index": null, "hypothesis_index": 23 }, { "op": "insert", "reference": null, "hypothesis": "no", "reference_index": null, "hypothesis_index": 24 }, { "op": "equal", "reference": "si", "hypothesis": "si", "reference_index": 21, "hypothesis_index": 25 }, { "op": "equal", "reference": "es", "hypothesis": "es", "reference_index": 22, "hypothesis_index": 26 }, { "op": "equal", "reference": "igual", "hypothesis": "igual", "reference_index": 23, "hypothesis_index": 27 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 24, "hypothesis_index": 28 }, { "op": "equal", "reference": "tonta", "hypothesis": "tonta", "reference_index": 25, "hypothesis_index": 29 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 26, "hypothesis_index": 30 }, { "op": "equal", "reference": "tú", "hypothesis": "tú", "reference_index": 27, "hypothesis_index": 31 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.67174, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Annoyed", "emotion_confidence": 0.66424560546875, "duration_seconds": 2.253, "mos": 3.3111, "audio_variant": "cleaned", "original_transcript_raw": "Menos mal, solo mil me gusta. ", "original_transcript": "Menos mal, solo mil me gusta.", "retranscribed_transcript": "O menos mal solo mil me gusta.", "backend": "qwen", "emotion_analyzed_seconds": 2.253, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-086", "energy": { "value": 0.66015625, "bucket": "high" }, "audio_url": "audio/utterance-086.wav", "spectrogram_url": "spectrograms/utterance-086.png", "waveform": [ 0.25742, 0.23135, 0.19876, 0.17966, 0.17111, 0.1729, 0.17649, 0.15715, 0.12544, 0.10245, 0.11521, 0.11862, 0.10665, 0.09282, 0.10078, 0.09035, 0.09314, 0.09548, 0.09028, 0.24791, 0.24021, 0.26846, 0.2644, 0.2776, 0.23328, 0.2419, 0.22196, 0.22114, 0.14323, 0.12999, 0.12637, 0.13699, 0.15874, 0.23768, 0.25592, 0.25812, 0.24046, 0.26892, 0.25848, 0.23142, 0.12795, 0.05816, 0.03832, 0.03316, 0.01457, 0.01267, 0.01693, 0.0585, 0.08863, 0.09597, 0.09739, 0.09238, 0.09876, 0.14281, 0.19952, 0.19169, 0.20593, 0.2221, 0.24848, 0.25644, 0.23864, 0.27659, 0.28292, 0.27399, 0.29789, 0.31884, 0.29904, 0.26061, 0.21339, 0.19226, 0.19798, 0.23112, 0.22002, 0.17074, 0.10156, 0.05469, 0.03964, 0.03668, 0.04072, 0.03307, 0.03968, 0.04071, 0.02757, 0.03138, 0.11497, 0.28703, 0.30872, 0.34726, 0.33763, 0.28552, 0.2753, 0.2486, 0.22693, 0.19167, 0.23264, 0.22087, 0.21815, 0.23584, 0.24385, 0.22571, 0.09338, 0.08029, 0.09474, 0.09173, 0.09058, 0.09756, 0.14407, 0.17119, 0.19649, 0.20959, 0.21508, 0.21518, 0.17465, 0.13876, 0.10714, 0.12215, 0.1236, 0.1176, 0.08266, 0.08157, 0.0841, 0.07807, 0.06977, 0.06905, 0.06889, 0.0657, 0.0711, 0.2876, 0.27034, 0.29493, 0.29303, 0.28485, 0.25995, 0.25861, 0.1648, 0.10581, 0.0692, 0.04262, 0.03136, 0.02619, 0.03554, 0.09536, 0.13654, 0.14525, 0.14982, 0.16174, 0.17032, 0.1565, 0.14751, 0.15156, 0.17903, 0.23042, 0.26811, 0.1224, 0.07391, 0.03958, 0.03371, 0.02864, 0.02319, 0.01119, 0.00513, 0.00161, 0.00108, 0.00064, 0.00056, 0.00363, 0.15776, 0.22733, 0.31058, 0.24589, 0.20427, 0.159, 0.11908, 0.10901, 0.07825, 0.05479, 0.06882, 0.04795, 0.03066, 0.01291 ], "comparison": { "original": "Menos mal, solo mil me gusta.", "retranscribed": "O menos mal solo mil me gusta.", "reference_tokens": [ "menos", "mal", "solo", "mil", "me", "gusta" ], "hypothesis_tokens": [ "o", "menos", "mal", "solo", "mil", "me", "gusta" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 6, "reference_words": 6, "hypothesis_words": 7, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "o", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "menos", "hypothesis": "menos", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "mal", "hypothesis": "mal", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "solo", "hypothesis": "solo", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "mil", "hypothesis": "mil", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "gusta", "hypothesis": "gusta", "reference_index": 5, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.34726, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Annoyed", "emotion_confidence": 0.4354877471923828, "duration_seconds": 2.7990000000000066, "mos": 2.8254, "audio_variant": "cleaned", "original_transcript_raw": "Ese ciudad es allá en Ativa. ", "original_transcript": "Ese ciudad es allá en Ativa.", "retranscribed_transcript": "Necesarios allá nativa", "backend": "qwen", "emotion_analyzed_seconds": 2.799, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-087", "energy": { "value": 0.62109375, "bucket": "high" }, "audio_url": "audio/utterance-087.wav", "spectrogram_url": "spectrograms/utterance-087.png", "waveform": [ 0.22914, 0.17208, 0.16233, 0.1481, 0.11109, 0.09575, 0.06931, 0.06946, 0.07547, 0.19537, 0.44748, 0.42917, 0.32729, 0.14583, 0.16658, 0.07418, 0.06048, 0.05205, 0.04796, 0.1836, 0.22901, 0.28329, 0.30617, 0.28875, 0.31897, 0.29404, 0.30288, 0.43723, 0.60075, 0.47046, 0.40251, 0.39831, 0.32968, 0.33146, 0.34917, 0.3247, 0.35302, 0.35266, 0.33031, 0.33035, 0.32132, 0.28449, 0.26854, 0.24122, 0.17759, 0.19267, 0.24248, 0.24672, 0.24015, 0.22264, 0.21329, 0.16828, 0.11027, 0.0452, 0.01859, 0.01582, 0.01252, 0.04113, 0.04721, 0.05879, 0.05332, 0.05587, 0.05495, 0.06801, 0.06349, 0.05374, 0.04013, 0.04107, 0.03809, 0.03319, 0.02299, 0.01012, 0.00966, 0.00974, 0.00458, 0.00307, 0.00142, 0.00162, 0.00412, 0.01026, 0.02224, 0.03005, 0.03307, 0.03678, 0.03166, 0.03445, 0.0359, 0.02472, 0.03172, 0.02765, 0.02875, 0.02877, 0.02993, 0.02755, 0.02756, 0.02272, 0.02409, 0.02488, 0.02339, 0.02604, 0.02099, 0.02101, 0.01816, 0.01544, 0.01181, 0.0143, 0.01538, 0.0132, 0.01058, 0.01357, 0.00918, 0.00598, 0.00287, 0.00121, 0.00125, 0.00126, 0.00146, 0.01919, 0.1958, 0.07552, 0.12108, 0.13589, 0.16635, 0.17772, 0.27312, 0.29097, 0.29878, 0.21038, 0.11811, 0.11223, 0.20178, 0.27845, 0.53808, 0.55074, 0.40002, 0.3981, 0.34315, 0.24797, 0.18832, 0.18062, 0.18985, 0.20659, 0.37131, 0.31254, 0.33386, 0.40192, 0.43001, 0.40831, 0.4265, 0.38441, 0.29184, 0.15369, 0.06921, 0.02564, 0.00504, 0.00124, 0.0357, 0.03838, 0.25621, 0.33642, 0.35605, 0.36582, 0.39235, 0.37891, 0.37439, 0.41509, 0.66547, 0.74489, 0.55866, 0.38337, 0.59993, 0.61985, 0.45208, 0.36536, 0.36173, 0.34868, 0.35186, 0.26277, 0.22176, 0.16871 ], "comparison": { "original": "Ese ciudad es allá en Ativa.", "retranscribed": "Necesarios allá nativa", "reference_tokens": [ "ese", "ciudad", "es", "allá", "en", "ativa" ], "hypothesis_tokens": [ "necesarios", "allá", "nativa" ], "counts": { "substitutions": 2, "deletions": 3, "insertions": 0, "hits": 1, "reference_words": 6, "hypothesis_words": 3, "edits": 5 }, "wer": 0.8333333333333334, "wer_percent": 83.33333333333334, "alignment": [ { "op": "delete", "reference": "ese", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "delete", "reference": "ciudad", "hypothesis": null, "reference_index": 1, "hypothesis_index": null }, { "op": "substitute", "reference": "es", "hypothesis": "necesarios", "reference_index": 2, "hypothesis_index": 0 }, { "op": "equal", "reference": "allá", "hypothesis": "allá", "reference_index": 3, "hypothesis_index": 1 }, { "op": "delete", "reference": "en", "hypothesis": null, "reference_index": 4, "hypothesis_index": null }, { "op": "substitute", "reference": "ativa", "hypothesis": "nativa", "reference_index": 5, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.74489, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Disgusted", "emotion_confidence": 0.2949497401714325, "duration_seconds": 1.9969999999999999, "mos": 2.8065, "audio_variant": "cleaned", "original_transcript_raw": "Como de tu altura es más guapo que yo. ", "original_transcript": "Como de tu altura es más guapo que yo.", "retranscribed_transcript": "es como de tu altura es más guapo que yo", "backend": "qwen", "emotion_analyzed_seconds": 1.997, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-088", "energy": { "value": 0.69140625, "bucket": "high" }, "audio_url": "audio/utterance-088.wav", "spectrogram_url": "spectrograms/utterance-088.png", "waveform": [ 0.00466, 0.05832, 0.2109, 0.4119, 0.51504, 0.42635, 0.27773, 0.15202, 0.05777, 0.08434, 0.06937, 0.02587, 0.00628, 0.01103, 0.00815, 0.12444, 0.25829, 0.10968, 0.22967, 0.29733, 0.21504, 0.13901, 0.15788, 0.1613, 0.14104, 0.29119, 0.3246, 0.35924, 0.35335, 0.30326, 0.14041, 0.08416, 0.01889, 0.02576, 0.08721, 0.46482, 0.42837, 0.39339, 0.3688, 0.24658, 0.03992, 0.00752, 0.00191, 0.001, 0.08025, 0.05596, 0.38163, 0.48563, 0.56915, 0.67324, 0.54042, 0.34584, 0.19244, 0.14153, 0.08992, 0.05139, 0.02442, 0.00432, 0.00073, 0.00064, 0.00086, 0.0984, 0.30926, 0.4041, 0.29879, 0.29067, 0.28119, 0.2783, 0.31208, 0.32491, 0.34785, 0.17499, 0.15096, 0.08382, 0.16263, 0.30025, 0.22636, 0.18065, 0.17669, 0.13689, 0.11892, 0.08157, 0.07828, 0.04459, 0.02926, 0.02574, 0.01906, 0.01369, 0.00502, 0.00131, 0.00112, 0.11374, 0.49831, 0.6289, 0.4386, 0.31674, 0.31835, 0.21671, 0.15254, 0.12338, 0.0937, 0.04539, 0.04291, 0.04768, 0.05717, 0.06168, 0.07256, 0.12061, 0.16859, 0.22961, 0.41963, 0.40328, 0.68277, 0.7132, 0.53718, 0.50992, 0.26461, 0.20595, 0.09868, 0.06295, 0.05622, 0.04748, 0.05644, 0.02832, 0.04949, 0.06028, 0.06287, 0.07135, 0.15754, 0.17868, 0.41352, 0.21245, 0.26207, 0.27386, 0.3017, 0.30485, 0.2562, 0.04152, 0.03689, 0.03421, 0.01642, 0.00681, 0.03656, 0.15101, 0.16546, 0.12232, 0.11797, 0.06699, 0.04701, 0.0273, 0.03056, 0.07533, 0.2104, 0.53749, 0.58444, 0.46118, 0.34826, 0.22429, 0.11332, 0.08254, 0.06176, 0.05987, 0.1193, 0.22512, 0.26098, 0.25808, 0.19509, 0.14465, 0.16258, 0.1706, 0.15307, 0.08817, 0.05875, 0.02638, 0.02244, 0.00233, 0.00221, 0.00348, 0.00389, 0.0064 ], "comparison": { "original": "Como de tu altura es más guapo que yo.", "retranscribed": "es como de tu altura es más guapo que yo", "reference_tokens": [ "como", "de", "tu", "altura", "es", "más", "guapo", "que", "yo" ], "hypothesis_tokens": [ "es", "como", "de", "tu", "altura", "es", "más", "guapo", "que", "yo" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 9, "reference_words": 9, "hypothesis_words": 10, "edits": 1 }, "wer": 0.1111111111111111, "wer_percent": 11.11111111111111, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "es", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "como", "hypothesis": "como", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "tu", "hypothesis": "tu", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "altura", "hypothesis": "altura", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "es", "hypothesis": "es", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "más", "hypothesis": "más", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "guapo", "hypothesis": "guapo", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 7, "hypothesis_index": 8 }, { "op": "equal", "reference": "yo", "hypothesis": "yo", "reference_index": 8, "hypothesis_index": 9 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.7132, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Disgusted", "emotion_confidence": 0.2699878513813019, "duration_seconds": 0.7169999999999845, "mos": 3.0812, "audio_variant": "cleaned", "original_transcript_raw": "А призовулся? ", "original_transcript": "А призовулся?", "retranscribed_transcript": "Es precioso.", "backend": "qwen", "emotion_analyzed_seconds": 0.717, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-089", "energy": { "value": 0.68359375, "bucket": "high" }, "audio_url": "audio/utterance-089.wav", "spectrogram_url": "spectrograms/utterance-089.png", "waveform": [ 0.0782, 0.10193, 0.11674, 0.12197, 0.11837, 0.13987, 0.17443, 0.21947, 0.26599, 0.2925, 0.25242, 0.23076, 0.21942, 0.1848, 0.13759, 0.10514, 0.09018, 0.08619, 0.08746, 0.0709, 0.06444, 0.03801, 0.04906, 0.03719, 0.02697, 0.02827, 0.02475, 0.02005, 0.01683, 0.01803, 0.01246, 0.02183, 0.04069, 0.07624, 0.11976, 0.18037, 0.21819, 0.20689, 0.2006, 0.14733, 0.10761, 0.09486, 0.09478, 0.124, 0.13577, 0.19748, 0.2284, 0.26284, 0.28966, 0.29266, 0.29004, 0.28838, 0.30195, 0.29049, 0.28285, 0.27191, 0.27448, 0.27852, 0.27475, 0.28413, 0.26403, 0.26661, 0.23294, 0.18454, 0.21307, 0.17932, 0.14206, 0.14077, 0.11053, 0.10762, 0.09294, 0.09134, 0.07725, 0.06736, 0.0454, 0.06567, 0.05697, 0.06152, 0.1225, 0.09929, 0.10275, 0.11311, 0.08796, 0.0635, 0.0843, 0.08768, 0.08393, 0.05036, 0.06576, 0.15303, 0.18172, 0.22409, 0.30993, 0.30026, 0.35093, 0.37041, 0.37702, 0.41559, 0.45995, 0.45279, 0.44291, 0.46449, 0.41367, 0.39611, 0.35747, 0.3526, 0.34667, 0.34952, 0.33426, 0.28975, 0.28362, 0.24178, 0.23291, 0.22215, 0.23723, 0.23682, 0.25827, 0.22049, 0.22989, 0.20261, 0.20248, 0.1785, 0.17237, 0.13991, 0.11822, 0.10741, 0.09145, 0.0735, 0.08894, 0.0575, 0.06975, 0.06828, 0.06667, 0.06479, 0.06306, 0.08364, 0.06201, 0.05049, 0.05706, 0.06169, 0.07011, 0.06527, 0.06306, 0.08452, 0.06279, 0.06551, 0.07435, 0.07512, 0.07333, 0.0679, 0.06251, 0.05777, 0.05638, 0.04659, 0.04881, 0.04813, 0.04107, 0.03223, 0.02813, 0.02426, 0.02197, 0.01885, 0.01882, 0.01618, 0.01544, 0.01028, 0.00879, 0.00737, 0.00608, 0.00566, 0.00584, 0.00455, 0.00989, 0.01154, 0.00901, 0.0189, 0.01486, 0.01045, 0.01268, 0.01941 ], "comparison": { "original": "А призовулся?", "retranscribed": "Es precioso.", "reference_tokens": [ "а", "призовулся" ], "hypothesis_tokens": [ "es", "precioso" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 0, "reference_words": 2, "hypothesis_words": 2, "edits": 2 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "substitute", "reference": "а", "hypothesis": "es", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "призовулся", "hypothesis": "precioso", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.46449, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Disgusted", "emotion_confidence": 0.2529665529727936, "duration_seconds": 0.9039999999999964, "mos": 2.9671, "audio_variant": "cleaned", "original_transcript_raw": "Экстрания музыка. ", "original_transcript": "Экстрания музыка.", "retranscribed_transcript": "Extraño mucho.", "backend": "qwen", "emotion_analyzed_seconds": 0.904, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-090", "energy": { "value": 0.6328125, "bucket": "high" }, "audio_url": "audio/utterance-090.wav", "spectrogram_url": "spectrograms/utterance-090.png", "waveform": [ 0.02227, 0.01284, 0.01272, 0.00594, 0.01062, 0.01127, 0.03811, 0.09642, 0.16859, 0.16984, 0.15844, 0.16665, 0.17368, 0.18504, 0.20128, 0.22481, 0.23218, 0.26427, 0.26022, 0.25795, 0.24761, 0.24271, 0.19882, 0.16502, 0.0635, 0.02973, 0.02035, 0.00796, 0.00336, 0.00351, 0.00846, 0.05213, 0.04349, 0.01713, 0.0294, 0.02631, 0.02206, 0.02314, 0.02208, 0.02367, 0.03064, 0.01962, 0.02408, 0.02693, 0.02164, 0.01368, 0.00891, 0.00429, 0.0013, 0.00066, 0.0003, 0.00014, 0.00015, 8e-05, 8e-05, 8e-05, 0.0001, 0.00012, 0.00033, 0.00332, 0.00459, 0.00824, 0.01293, 0.02076, 0.04459, 0.07409, 0.12398, 0.12675, 0.12515, 0.12137, 0.11108, 0.05662, 0.0483, 0.1069, 0.11972, 0.13238, 0.14042, 0.12504, 0.14627, 0.13656, 0.1347, 0.14494, 0.14577, 0.13929, 0.15491, 0.15399, 0.12275, 0.10748, 0.11032, 0.10986, 0.10149, 0.07648, 0.06594, 0.06202, 0.06288, 0.05616, 0.05322, 0.06098, 0.0647, 0.06419, 0.05547, 0.06079, 0.05748, 0.05715, 0.05658, 0.05442, 0.05871, 0.06594, 0.06805, 0.07283, 0.04316, 0.06873, 0.05925, 0.05685, 0.05719, 0.05086, 0.04837, 0.05065, 0.04964, 0.04777, 0.04675, 0.04355, 0.04181, 0.03794, 0.03704, 0.02947, 0.03845, 0.03964, 0.03987, 0.03759, 0.03778, 0.03781, 0.03413, 0.03628, 0.03592, 0.03552, 0.03565, 0.03559, 0.0357, 0.03467, 0.03091, 0.03312, 0.03431, 0.03271, 0.03188, 0.03102, 0.02986, 0.02671, 0.0214, 0.02249, 0.02091, 0.01796, 0.0152, 0.0153, 0.01232, 0.00863, 0.00751, 0.00221, 0.00185, 0.00116, 0.00109, 0.001, 0.00179, 0.00143, 0.00282, 0.00143, 0.00061, 0.00023, 0.00015, 0.00021, 0.00215, 0.00285, 0.00489, 0.00694, 0.00702, 0.0095, 0.02236, 0.025, 0.03304, 0.05171 ], "comparison": { "original": "Экстрания музыка.", "retranscribed": "Extraño mucho.", "reference_tokens": [ "экстрания", "музыка" ], "hypothesis_tokens": [ "extraño", "mucho" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 0, "reference_words": 2, "hypothesis_words": 2, "edits": 2 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "substitute", "reference": "экстрания", "hypothesis": "extraño", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "музыка", "hypothesis": "mucho", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.26427, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Fearful", "emotion_confidence": 0.3126034736633301, "duration_seconds": 0.7509999999999764, "mos": 3.1236, "audio_variant": "original", "original_transcript_raw": "No sé cómo. ", "original_transcript": "No sé cómo.", "retranscribed_transcript": "No sé cómo.", "backend": "qwen", "emotion_analyzed_seconds": 0.751, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-091", "energy": { "value": 0.498046875, "bucket": "low" }, "audio_url": "audio/utterance-091.wav", "spectrogram_url": "spectrograms/utterance-091.png", "waveform": [ 0.03282, 0.03834, 0.02461, 0.02813, 0.03382, 0.03587, 0.02304, 0.03012, 0.03215, 0.0543, 0.03222, 0.0551, 0.1225, 0.19384, 0.1589, 0.16203, 0.12724, 0.19498, 0.14255, 0.16803, 0.23354, 0.17336, 0.17582, 0.15854, 0.20236, 0.16328, 0.16226, 0.13225, 0.13958, 0.11857, 0.09691, 0.08805, 0.07882, 0.12117, 0.08912, 0.0698, 0.08761, 0.0761, 0.08843, 0.12917, 0.07951, 0.06176, 0.12424, 0.11356, 0.08983, 0.0693, 0.09004, 0.07003, 0.07563, 0.09081, 0.07843, 0.0839, 0.10412, 0.07421, 0.08141, 0.08057, 0.07273, 0.0428, 0.04785, 0.04368, 0.06049, 0.10133, 0.11547, 0.15822, 0.16681, 0.10637, 0.13186, 0.11947, 0.14793, 0.0947, 0.07013, 0.048, 0.03422, 0.03826, 0.02743, 0.03958, 0.02179, 0.03334, 0.03403, 0.03528, 0.01303, 0.02532, 0.02676, 0.02458, 0.01946, 0.02871, 0.02012, 0.03213, 0.02084, 0.03045, 0.03734, 0.04187, 0.03419, 0.03314, 0.0664, 0.10795, 0.0519, 0.0426, 0.05553, 0.03369, 0.05025, 0.08248, 0.10422, 0.10878, 0.09913, 0.08981, 0.12583, 0.11919, 0.11544, 0.11099, 0.15869, 0.15847, 0.12455, 0.12566, 0.12866, 0.11418, 0.10038, 0.12762, 0.12353, 0.10676, 0.15024, 0.11774, 0.13927, 0.11807, 0.13573, 0.12449, 0.11421, 0.12927, 0.11541, 0.08365, 0.08461, 0.06937, 0.10105, 0.07718, 0.07354, 0.08343, 0.04924, 0.10034, 0.0672, 0.08897, 0.06228, 0.04381, 0.03585, 0.05225, 0.02611, 0.08725, 0.04714, 0.07658, 0.07717, 0.04622, 0.0357, 0.04247, 0.03521, 0.03611, 0.05331, 0.03583, 0.03822, 0.03535, 0.03219, 0.04046, 0.03185, 0.05487, 0.04228, 0.04478, 0.03735, 0.04155, 0.02482, 0.02716, 0.03238, 0.03022, 0.0188, 0.02371, 0.0217, 0.0399, 0.02149, 0.0422, 0.01961, 0.04152, 0.02786, 0.03689 ], "comparison": { "original": "No sé cómo.", "retranscribed": "No sé cómo.", "reference_tokens": [ "no", "sé", "cómo" ], "hypothesis_tokens": [ "no", "sé", "cómo" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 3, "reference_words": 3, "hypothesis_words": 3, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "sé", "hypothesis": "sé", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "cómo", "hypothesis": "cómo", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.23354, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Fearful", "emotion_confidence": 0.519861102104187, "duration_seconds": 2.1499999999999773, "mos": 3.426, "audio_variant": "cleaned", "original_transcript_raw": "Qué¿ pasa con Walter? ", "original_transcript": "Qué¿ pasa con Walter?", "retranscribed_transcript": "¿Qué pasa con Walter?", "backend": "qwen", "emotion_analyzed_seconds": 2.15, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-092", "energy": { "value": 0.5078125, "bucket": "low" }, "audio_url": "audio/utterance-092.wav", "spectrogram_url": "spectrograms/utterance-092.png", "waveform": [ 0.01117, 0.0273, 0.08239, 0.13234, 0.13737, 0.17186, 0.12193, 0.14719, 0.15581, 0.1797, 0.19361, 0.25798, 0.2468, 0.23775, 0.22323, 0.16248, 0.16359, 0.15356, 0.1567, 0.13758, 0.08915, 0.0316, 0.0081, 0.00748, 0.00198, 0.0011, 0.00048, 0.00046, 0.00033, 0.00036, 0.00023, 0.00021, 0.00021, 0.0002, 0.00025, 0.00024, 0.00024, 0.00014, 0.00013, 0.00017, 0.00019, 0.00019, 0.00026, 0.00023, 0.00021, 0.00016, 0.00013, 0.00026, 0.00029, 0.00019, 0.00025, 0.00023, 0.00021, 0.00024, 0.00026, 0.00025, 0.0002, 0.00025, 0.00026, 0.00024, 0.00026, 0.00031, 0.00025, 0.00032, 0.00022, 0.00032, 0.00025, 0.00027, 0.00027, 0.0003, 0.00031, 0.00036, 0.00035, 0.00031, 0.0003, 0.00052, 0.00409, 0.10282, 0.31837, 0.4019, 0.46122, 0.48558, 0.36027, 0.12034, 0.02424, 0.00582, 0.00323, 0.00333, 0.002, 0.00106, 0.00078, 0.00064, 0.00051, 0.00045, 0.00047, 0.0006, 0.00801, 0.00619, 0.40082, 0.48981, 0.49851, 0.55133, 0.53719, 0.56625, 0.47053, 0.41907, 0.31746, 0.13355, 0.09466, 0.02719, 0.0215, 0.06182, 0.06016, 0.0793, 0.27545, 0.35309, 0.32214, 0.26289, 0.17005, 0.01981, 0.00454, 0.00199, 0.00157, 0.14387, 0.10607, 0.40372, 0.36724, 0.36752, 0.38106, 0.38717, 0.34057, 0.29259, 0.27421, 0.25421, 0.23187, 0.1986, 0.141, 0.10457, 0.1416, 0.18423, 0.23311, 0.26616, 0.31247, 0.32511, 0.30904, 0.34301, 0.34038, 0.41686, 0.36897, 0.32072, 0.18249, 0.14212, 0.09717, 0.05596, 0.00697, 0.00465, 0.00147, 0.09008, 0.06041, 0.13408, 0.13423, 0.13471, 0.13978, 0.11832, 0.1071, 0.08518, 0.08963, 0.06353, 0.0711, 0.04422, 0.04817, 0.04036, 0.02398, 0.01106, 0.01208, 0.00467, 0.00403, 0.00292, 0.00397, 0.02844 ], "comparison": { "original": "Qué¿ pasa con Walter?", "retranscribed": "¿Qué pasa con Walter?", "reference_tokens": [ "qué", "pasa", "con", "walter" ], "hypothesis_tokens": [ "qué", "pasa", "con", "walter" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 4, "reference_words": 4, "hypothesis_words": 4, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "qué", "hypothesis": "qué", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "pasa", "hypothesis": "pasa", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "con", "hypothesis": "con", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "walter", "hypothesis": "walter", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.56625, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Fearful", "emotion_confidence": 0.27677619457244873, "duration_seconds": 3.328000000000003, "mos": 3.4944, "audio_variant": "original", "original_transcript_raw": "Ay Dios estas big", "original_transcript": "Ay Dios estas big", "retranscribed_transcript": "Ay dios, estás bien.", "backend": "qwen", "emotion_analyzed_seconds": 3.328, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-093", "energy": { "value": 0.466796875, "bucket": "low" }, "audio_url": "audio/utterance-093.wav", "spectrogram_url": "spectrograms/utterance-093.png", "waveform": [ 0.0255, 0.01939, 0.01832, 0.00765, 0.00508, 0.00535, 0.01803, 0.01673, 0.01185, 0.00738, 0.00416, 0.00225, 0.00472, 0.00485, 0.01714, 0.01296, 0.01224, 0.00661, 0.00337, 0.00386, 0.0119, 0.02672, 0.03818, 0.03782, 0.03493, 0.03548, 0.03293, 0.03585, 0.02763, 0.03355, 0.0302, 0.02866, 0.02121, 0.02593, 0.03593, 0.0431, 0.04211, 0.0395, 0.02584, 0.01334, 0.00831, 0.00415, 0.00359, 0.01579, 0.00706, 0.01613, 0.01277, 0.02122, 0.03031, 0.03079, 0.03054, 0.03051, 0.04064, 0.04173, 0.04267, 0.0334, 0.03281, 0.0387, 0.0373, 0.04335, 0.07048, 0.06699, 0.02586, 0.01214, 0.00801, 0.00775, 0.0079, 0.01037, 0.02095, 0.01564, 0.0126, 0.00982, 0.00816, 0.00845, 0.00909, 0.01115, 0.01515, 0.01358, 0.00773, 0.00894, 0.00499, 0.00847, 0.00655, 0.01548, 0.0179, 0.01347, 0.00708, 0.00427, 0.00297, 0.0022, 0.0051, 0.01621, 0.01439, 0.01206, 0.00736, 0.00354, 0.00277, 0.00494, 0.00672, 0.0172, 0.01474, 0.01158, 0.00935, 0.00673, 0.00605, 0.00781, 0.01386, 0.02092, 0.01522, 0.00903, 0.00738, 0.00707, 0.00502, 0.03058, 0.0616, 0.10363, 0.13225, 0.12237, 0.03589, 0.0149, 0.0089, 0.01347, 0.02482, 0.02149, 0.03006, 0.06535, 0.05023, 0.03594, 0.02661, 0.01575, 0.02304, 0.01678, 0.01319, 0.01266, 0.01022, 0.00319, 0.00667, 0.0155, 0.09228, 0.10291, 0.06194, 0.04419, 0.03556, 0.03897, 0.03829, 0.04618, 0.05253, 0.05347, 0.01972, 0.00658, 0.00555, 0.0046, 0.01748, 0.02612, 0.01185, 0.01162, 0.00682, 0.00268, 0.00176, 0.00458, 0.00822, 0.01843, 0.01231, 0.00897, 0.00644, 0.00363, 0.00308, 0.00524, 0.01553, 0.01633, 0.01233, 0.00666, 0.0051, 0.00422, 0.00368, 0.00684, 0.01902, 0.01955, 0.01406, 0.00755 ], "comparison": { "original": "Ay Dios estas big", "retranscribed": "Ay dios, estás bien.", "reference_tokens": [ "ay", "dios", "estas", "big" ], "hypothesis_tokens": [ "ay", "dios", "estás", "bien" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 4, "hypothesis_words": 4, "edits": 2 }, "wer": 0.5, "wer_percent": 50.0, "alignment": [ { "op": "equal", "reference": "ay", "hypothesis": "ay", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "dios", "hypothesis": "dios", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "estas", "hypothesis": "estás", "reference_index": 2, "hypothesis_index": 2 }, { "op": "substitute", "reference": "big", "hypothesis": "bien", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.13225, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Fearful", "emotion_confidence": 0.38333457708358765, "duration_seconds": 2.0309999999999997, "mos": 3.332, "audio_variant": "cleaned", "original_transcript_raw": "Imposible, los destruyó el incendio. ", "original_transcript": "Imposible, los destruyó el incendio.", "retranscribed_transcript": "Es imposible los destruyó el incendio.", "backend": "qwen", "emotion_analyzed_seconds": 2.031, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-094", "energy": { "value": 0.53125, "bucket": "medium" }, "audio_url": "audio/utterance-094.wav", "spectrogram_url": "spectrograms/utterance-094.png", "waveform": [ 0.00183, 0.00208, 0.00424, 0.03035, 0.05224, 0.04735, 0.04403, 0.03868, 0.03006, 0.01899, 0.02151, 0.02334, 0.02579, 0.02905, 0.02229, 0.01815, 0.03118, 0.03587, 0.04036, 0.04041, 0.03952, 0.03795, 0.03876, 0.03533, 0.0247, 0.02075, 0.00689, 0.00443, 0.01105, 0.01259, 0.04373, 0.05288, 0.04878, 0.04437, 0.03966, 0.03029, 0.02341, 0.01647, 0.01911, 0.01878, 0.02474, 0.02044, 0.02281, 0.03004, 0.03238, 0.02464, 0.02264, 0.03274, 0.02881, 0.03167, 0.04202, 0.05569, 0.06094, 0.0559, 0.05152, 0.04527, 0.03847, 0.02187, 0.01716, 0.01825, 0.02656, 0.02741, 0.03289, 0.03227, 0.04935, 0.04891, 0.05538, 0.0527, 0.05001, 0.04901, 0.05001, 0.04045, 0.03063, 0.02952, 0.02862, 0.03069, 0.03216, 0.04582, 0.0499, 0.04795, 0.04414, 0.03851, 0.0352, 0.02328, 0.02135, 0.01779, 0.01443, 0.01112, 0.01449, 0.02462, 0.03029, 0.03447, 0.04206, 0.03656, 0.02585, 0.01635, 0.01316, 0.00844, 0.00196, 0.00061, 0.00127, 0.00944, 0.01058, 0.0073, 0.00865, 0.00618, 0.00548, 0.007, 0.03054, 0.03844, 0.0359, 0.03295, 0.02281, 0.00809, 0.00367, 0.00173, 0.01562, 0.02049, 0.01462, 0.0486, 0.04841, 0.05503, 0.05802, 0.0624, 0.05356, 0.04744, 0.0372, 0.03126, 0.02131, 0.02903, 0.03459, 0.03674, 0.03564, 0.03565, 0.03103, 0.02915, 0.02544, 0.02323, 0.02228, 0.01876, 0.01428, 0.01166, 0.01481, 0.02614, 0.01995, 0.0273, 0.01536, 0.0187, 0.01068, 0.02317, 0.02767, 0.02707, 0.02692, 0.02964, 0.02393, 0.01676, 0.01185, 0.01494, 0.01306, 0.01227, 0.01015, 0.00742, 0.00778, 0.01461, 0.02308, 0.02004, 0.02693, 0.02631, 0.02342, 0.02152, 0.01996, 0.01498, 0.01892, 0.02157, 0.015, 0.01134, 0.01121, 0.01118, 0.00952, 0.00916 ], "comparison": { "original": "Imposible, los destruyó el incendio.", "retranscribed": "Es imposible los destruyó el incendio.", "reference_tokens": [ "imposible", "los", "destruyó", "el", "incendio" ], "hypothesis_tokens": [ "es", "imposible", "los", "destruyó", "el", "incendio" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 5, "reference_words": 5, "hypothesis_words": 6, "edits": 1 }, "wer": 0.2, "wer_percent": 20.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "es", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "imposible", "hypothesis": "imposible", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "los", "hypothesis": "los", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "destruyó", "hypothesis": "destruyó", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "el", "hypothesis": "el", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "incendio", "hypothesis": "incendio", "reference_index": 4, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.0624, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Fearful", "emotion_confidence": 0.3728485107421875, "duration_seconds": 1.586999999999989, "mos": 3.4158, "audio_variant": "cleaned", "original_transcript_raw": "Mucha fiebre, puede morir. ", "original_transcript": "Mucha fiebre, puede morir.", "retranscribed_transcript": "Tiene mucha fiebre, puede morir.", "backend": "qwen", "emotion_analyzed_seconds": 1.587, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-095", "energy": { "value": 0.578125, "bucket": "medium" }, "audio_url": "audio/utterance-095.wav", "spectrogram_url": "spectrograms/utterance-095.png", "waveform": [ 0.06479, 0.29368, 0.36866, 0.38576, 0.38708, 0.4774, 0.47289, 0.41443, 0.29522, 0.33928, 0.34915, 0.35904, 0.44757, 0.49182, 0.5232, 0.4987, 0.49289, 0.42032, 0.23697, 0.26295, 0.27107, 0.27689, 0.28412, 0.28237, 0.31767, 0.33103, 0.34926, 0.32713, 0.29269, 0.27099, 0.13045, 0.01538, 0.00781, 0.00917, 0.02769, 0.37717, 0.33277, 0.19899, 0.10691, 0.25024, 0.37317, 0.30968, 0.31884, 0.31913, 0.27307, 0.1527, 0.08105, 0.03487, 0.01658, 0.01159, 0.01103, 0.0083, 0.00939, 0.01309, 0.03775, 0.04699, 0.05433, 0.08024, 0.1666, 0.20239, 0.23267, 0.31236, 0.35798, 0.47819, 0.55311, 0.6442, 0.6004, 0.47292, 0.26322, 0.09068, 0.06352, 0.02543, 0.02215, 0.01508, 0.05244, 0.32904, 0.42028, 0.37266, 0.12084, 0.23456, 0.38219, 0.5767, 0.5932, 0.5601, 0.51976, 0.10301, 0.03402, 0.01585, 0.00872, 0.008, 0.00317, 0.00302, 0.00178, 0.01488, 0.37601, 0.09571, 0.19637, 0.2215, 0.24544, 0.29136, 0.21645, 0.25977, 0.28221, 0.29741, 0.33622, 0.36914, 0.16673, 0.06316, 0.06737, 0.04486, 0.14198, 0.39094, 0.46821, 0.49646, 0.56883, 0.59868, 0.42828, 0.26497, 0.31435, 0.35023, 0.36191, 0.37136, 0.40463, 0.43376, 0.43699, 0.4281, 0.44442, 0.48221, 0.46099, 0.39607, 0.40916, 0.34264, 0.19983, 0.23851, 0.25881, 0.23344, 0.21036, 0.1766, 0.09196, 0.05792, 0.05925, 0.09324, 0.11361, 0.14428, 0.15434, 0.15894, 0.15908, 0.142, 0.10776, 0.10553, 0.08128, 0.09166, 0.07811, 0.08503, 0.07591, 0.09155, 0.1171, 0.11863, 0.14148, 0.12575, 0.11635, 0.10543, 0.0811, 0.04568, 0.02781, 0.02375, 0.01578, 0.01426, 0.01206, 0.00584, 0.00502, 0.00346, 0.00189, 0.00307, 0.01101, 0.03503, 0.03836, 0.1487, 0.16572, 0.18956 ], "comparison": { "original": "Mucha fiebre, puede morir.", "retranscribed": "Tiene mucha fiebre, puede morir.", "reference_tokens": [ "mucha", "fiebre", "puede", "morir" ], "hypothesis_tokens": [ "tiene", "mucha", "fiebre", "puede", "morir" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 4, "reference_words": 4, "hypothesis_words": 5, "edits": 1 }, "wer": 0.25, "wer_percent": 25.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "tiene", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "mucha", "hypothesis": "mucha", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "fiebre", "hypothesis": "fiebre", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "puede", "hypothesis": "puede", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "morir", "hypothesis": "morir", "reference_index": 3, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.6442, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Fearful", "emotion_confidence": 0.6160674095153809, "duration_seconds": 0.9730000000000132, "mos": 3.5005, "audio_variant": "original", "original_transcript_raw": "Я готову и да. ", "original_transcript": "Я готову и да.", "retranscribed_transcript": "dije que te fueras", "backend": "qwen", "emotion_analyzed_seconds": 0.973, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-096", "energy": { "value": 0.57421875, "bucket": "medium" }, "audio_url": "audio/utterance-096.wav", "spectrogram_url": "spectrograms/utterance-096.png", "waveform": [ 0.05064, 0.07726, 0.06464, 0.06174, 0.06528, 0.06379, 0.05707, 0.05282, 0.07602, 0.04929, 0.06012, 0.06338, 0.05695, 0.04224, 0.04507, 0.07302, 0.05741, 0.04646, 0.05305, 0.04633, 0.05884, 0.02851, 0.02371, 0.01536, 0.015, 0.01297, 0.01061, 0.01292, 0.01334, 0.01182, 0.01003, 0.00919, 0.0536, 0.10056, 0.09306, 0.03544, 0.05023, 0.04796, 0.03292, 0.06636, 0.04444, 0.05568, 0.03086, 0.01826, 0.00808, 0.01259, 0.01423, 0.01386, 0.0143, 0.01133, 0.012, 0.01033, 0.01507, 0.00892, 0.08373, 0.06564, 0.03382, 0.03207, 0.06079, 0.04816, 0.05342, 0.04708, 0.0383, 0.03868, 0.03934, 0.0231, 0.01567, 0.01148, 0.01377, 0.01344, 0.016, 0.01772, 0.01426, 0.01545, 0.01996, 0.02502, 0.01618, 0.01952, 0.01881, 0.01238, 0.0161, 0.03652, 0.02816, 0.0339, 0.04383, 0.05231, 0.08744, 0.06444, 0.07967, 0.05836, 0.10943, 0.04897, 0.07268, 0.052, 0.05093, 0.05859, 0.07048, 0.0408, 0.03138, 0.05077, 0.02252, 0.02132, 0.01699, 0.01951, 0.02475, 0.02669, 0.01978, 0.03236, 0.02347, 0.02827, 0.04508, 0.04804, 0.07866, 0.06847, 0.07579, 0.10403, 0.11891, 0.12137, 0.16904, 0.1008, 0.11751, 0.08534, 0.10193, 0.10235, 0.09442, 0.07387, 0.0671, 0.06138, 0.04752, 0.05314, 0.03981, 0.04539, 0.03672, 0.04705, 0.06259, 0.09791, 0.12017, 0.07496, 0.07708, 0.06026, 0.08527, 0.06259, 0.10764, 0.12077, 0.1046, 0.10194, 0.09695, 0.07428, 0.0769, 0.07707, 0.07029, 0.04208, 0.0345, 0.03092, 0.03137, 0.03467, 0.01819, 0.0149, 0.01148, 0.01059, 0.01248, 0.00806, 0.01155, 0.00894, 0.0087, 0.0114, 0.01239, 0.00892, 0.01044, 0.0088, 0.01346, 0.0099, 0.01019, 0.01036, 0.01045, 0.00957, 0.01118, 0.01288, 0.00715, 0.01349 ], "comparison": { "original": "Я готову и да.", "retranscribed": "dije que te fueras", "reference_tokens": [ "я", "готову", "и", "да" ], "hypothesis_tokens": [ "dije", "que", "te", "fueras" ], "counts": { "substitutions": 4, "deletions": 0, "insertions": 0, "hits": 0, "reference_words": 4, "hypothesis_words": 4, "edits": 4 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "substitute", "reference": "я", "hypothesis": "dije", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "готову", "hypothesis": "que", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "и", "hypothesis": "te", "reference_index": 2, "hypothesis_index": 2 }, { "op": "substitute", "reference": "да", "hypothesis": "fueras", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.16904, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Fearful", "emotion_confidence": 0.3535310626029968, "duration_seconds": 1.3480000000000132, "mos": 3.6162, "audio_variant": "cleaned", "original_transcript_raw": "О Диос", "original_transcript": "О Диос", "retranscribed_transcript": "Oh Dios.", "backend": "qwen", "emotion_analyzed_seconds": 1.348, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-097", "energy": { "value": 0.83203125, "bucket": "high" }, "audio_url": "audio/utterance-097.wav", "spectrogram_url": "spectrograms/utterance-097.png", "waveform": [ 0.28905, 0.25546, 0.25076, 0.16303, 0.16776, 0.18695, 0.23842, 0.25502, 0.23985, 0.19215, 0.17469, 0.18303, 0.16171, 0.14269, 0.14, 0.12149, 0.15687, 0.17823, 0.14185, 0.18884, 0.17706, 0.12806, 0.14863, 0.10753, 0.10607, 0.04635, 0.04238, 0.03452, 0.03368, 0.03367, 0.02664, 0.02681, 0.02665, 0.02635, 0.0327, 0.03206, 0.03572, 0.03019, 0.03015, 0.0264, 0.02388, 0.01976, 0.01934, 0.02192, 0.03157, 0.0581, 0.10065, 0.1545, 0.2018, 0.20961, 0.18522, 0.20901, 0.18301, 0.14598, 0.14683, 0.11864, 0.06524, 0.13293, 0.19377, 0.21932, 0.22875, 0.24868, 0.31629, 0.32283, 0.37197, 0.34382, 0.4239, 0.56408, 0.57469, 0.54716, 0.48487, 0.36579, 0.29371, 0.25255, 0.24432, 0.24976, 0.25536, 0.28833, 0.313, 0.34402, 0.36181, 0.35992, 0.38033, 0.40219, 0.41018, 0.39561, 0.3331, 0.32246, 0.3046, 0.26562, 0.258, 0.25195, 0.20823, 0.18238, 0.15421, 0.16539, 0.19283, 0.20455, 0.20642, 0.17743, 0.15375, 0.10115, 0.10716, 0.08768, 0.10411, 0.09632, 0.09435, 0.07378, 0.08995, 0.09357, 0.07323, 0.11391, 0.09457, 0.08157, 0.07375, 0.08076, 0.12409, 0.15036, 0.08448, 0.11486, 0.11574, 0.13139, 0.21709, 0.21718, 0.2023, 0.18492, 0.11876, 0.07193, 0.06365, 0.05289, 0.05078, 0.05283, 0.05073, 0.06049, 0.05834, 0.05733, 0.05993, 0.06403, 0.05653, 0.05854, 0.07025, 0.04084, 0.04728, 0.03798, 0.04717, 0.03443, 0.03802, 0.03578, 0.02632, 0.02462, 0.01399, 0.01428, 0.00943, 0.00777, 0.003, 0.00162, 0.00146, 0.00095, 0.0006, 0.00031, 0.00045, 0.00041, 0.00023, 0.0002, 9e-05, 0.0001, 6e-05, 3e-05, 4e-05, 3e-05, 6e-05, 4e-05, 3e-05, 0.00042, 0.00099, 0.0012, 0.00212, 0.00335, 0.00475, 0.00435 ], "comparison": { "original": "О Диос", "retranscribed": "Oh Dios.", "reference_tokens": [ "о", "диос" ], "hypothesis_tokens": [ "oh", "dios" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 0, "reference_words": 2, "hypothesis_words": 2, "edits": 2 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "substitute", "reference": "о", "hypothesis": "oh", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "диос", "hypothesis": "dios", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.57469, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Fearful", "emotion_confidence": 0.4374053180217743, "duration_seconds": 0.7340000000000089, "mos": 3.108, "audio_variant": "original", "original_transcript_raw": "perdona", "original_transcript": "perdona", "retranscribed_transcript": "Perdona.", "backend": "qwen", "emotion_analyzed_seconds": 0.734, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-098", "energy": { "value": 0.60546875, "bucket": "high" }, "audio_url": "audio/utterance-098.wav", "spectrogram_url": "spectrograms/utterance-098.png", "waveform": [ 0.30459, 0.31286, 0.30189, 0.31226, 0.31309, 0.31027, 0.29485, 0.29636, 0.28908, 0.28771, 0.27814, 0.27711, 0.25987, 0.26124, 0.25525, 0.22758, 0.12798, 0.15926, 0.23986, 0.26313, 0.27136, 0.27261, 0.26476, 0.25774, 0.17554, 0.10831, 0.09386, 0.09096, 0.08471, 0.08721, 0.08309, 0.07949, 0.08786, 0.07619, 0.06788, 0.1195, 0.13005, 0.16047, 0.23678, 0.26722, 0.29369, 0.30555, 0.31036, 0.29743, 0.29467, 0.30131, 0.30492, 0.29234, 0.28748, 0.29427, 0.29334, 0.29734, 0.28849, 0.28133, 0.28547, 0.29442, 0.28171, 0.2804, 0.2842, 0.28014, 0.26173, 0.26842, 0.25965, 0.26056, 0.26578, 0.26681, 0.2598, 0.22754, 0.20084, 0.20929, 0.24244, 0.23131, 0.22924, 0.22361, 0.20378, 0.21313, 0.21627, 0.21363, 0.2194, 0.22681, 0.22806, 0.22473, 0.21993, 0.2256, 0.25082, 0.26571, 0.25612, 0.26894, 0.27125, 0.28124, 0.27515, 0.27847, 0.27283, 0.22277, 0.2682, 0.25308, 0.22507, 0.25539, 0.22997, 0.24339, 0.24007, 0.23673, 0.23229, 0.23503, 0.2168, 0.24144, 0.21565, 0.19669, 0.18608, 0.20547, 0.1777, 0.17352, 0.19356, 0.17574, 0.19097, 0.17898, 0.15796, 0.16455, 0.14548, 0.1825, 0.16855, 0.18767, 0.15664, 0.13613, 0.14537, 0.12851, 0.11814, 0.09477, 0.0974, 0.06929, 0.04945, 0.03301, 0.02791, 0.01886, 0.01803, 0.01332, 0.01097, 0.01167, 0.00956, 0.01662, 0.02076, 0.02537, 0.03146, 0.0288, 0.03125, 0.04123, 0.04056, 0.03584, 0.04425, 0.03219, 0.04329, 0.04056, 0.04067, 0.04067, 0.03504, 0.0366, 0.04383, 0.04744, 0.05566, 0.05409, 0.03841, 0.06176, 0.07492, 0.07669, 0.05254, 0.03284, 0.0446, 0.06056, 0.07138, 0.05693, 0.05945, 0.05804, 0.05489, 0.07625, 0.08821, 0.0597, 0.06262, 0.08263, 0.04658, 0.05736 ], "comparison": { "original": "perdona", "retranscribed": "Perdona.", "reference_tokens": [ "perdona" ], "hypothesis_tokens": [ "perdona" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 1, "reference_words": 1, "hypothesis_words": 1, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "perdona", "hypothesis": "perdona", "reference_index": 0, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.31309, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Fearful", "emotion_confidence": 0.2600890100002289, "duration_seconds": 2.9009999999999536, "mos": 2.8646, "audio_variant": "cleaned", "original_transcript_raw": "No, no, no, no, no de gusto", "original_transcript": "No, no, no, no, no de gusto", "retranscribed_transcript": "no no no no beb bebop lee", "backend": "qwen", "emotion_analyzed_seconds": 2.901, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-099", "energy": { "value": 0.8046875, "bucket": "high" }, "audio_url": "audio/utterance-099.wav", "spectrogram_url": "spectrograms/utterance-099.png", "waveform": [ 0.37016, 0.46432, 0.55707, 0.59665, 0.59495, 0.57925, 0.56077, 0.32001, 0.20638, 0.18901, 0.17446, 0.24992, 0.52344, 0.52067, 0.54338, 0.54336, 0.56235, 0.50194, 0.42363, 0.23765, 0.22705, 0.21243, 0.20373, 0.20993, 0.31603, 0.38759, 0.42866, 0.40468, 0.3866, 0.35434, 0.21916, 0.2071, 0.18583, 0.1991, 0.23683, 0.30851, 0.51703, 0.41603, 0.32179, 0.43222, 0.40887, 0.32224, 0.31322, 0.32163, 0.4107, 0.41787, 0.53382, 0.5453, 0.42094, 0.39484, 0.34594, 0.26418, 0.16726, 0.07791, 0.07343, 0.11764, 0.12644, 0.122, 0.06424, 0.0616, 0.05372, 0.03933, 0.04013, 0.07546, 0.0656, 0.06735, 0.15321, 0.34478, 0.41343, 0.45415, 0.47496, 0.48384, 0.48067, 0.50492, 0.49915, 0.53776, 0.5575, 0.60208, 0.60785, 0.60364, 0.5946, 0.59784, 0.59559, 0.61568, 0.57774, 0.58102, 0.56683, 0.53635, 0.26425, 0.15676, 0.1375, 0.14577, 0.2206, 0.41274, 0.48427, 0.53714, 0.51918, 0.5369, 0.45469, 0.15445, 0.10735, 0.14181, 0.18225, 0.26714, 0.40076, 0.4372, 0.46833, 0.48509, 0.49653, 0.45691, 0.3984, 0.21581, 0.0571, 0.02297, 0.00314, 0.00068, 0.00056, 0.00195, 0.14881, 0.26158, 0.32251, 0.37511, 0.32111, 0.30508, 0.38715, 0.45319, 0.46678, 0.51549, 0.51135, 0.49396, 0.53806, 0.47262, 0.4494, 0.47629, 0.49059, 0.49864, 0.49276, 0.43778, 0.45878, 0.42051, 0.4001, 0.43022, 0.40509, 0.40464, 0.4146, 0.42202, 0.37991, 0.44838, 0.43158, 0.45251, 0.45042, 0.41133, 0.3405, 0.33284, 0.37084, 0.34885, 0.34018, 0.32009, 0.30057, 0.25732, 0.20425, 0.16028, 0.08753, 0.03856, 0.03112, 0.01774, 0.01218, 0.01214, 0.01013, 0.00942, 0.00819, 0.00476, 0.00206, 0.0006, 0.00019, 0.00011, 0.00024, 0.00455, 0.00494, 0.00691 ], "comparison": { "original": "No, no, no, no, no de gusto", "retranscribed": "no no no no beb bebop lee", "reference_tokens": [ "no", "no", "no", "no", "no", "de", "gusto" ], "hypothesis_tokens": [ "no", "no", "no", "no", "beb", "bebop", "lee" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 0, "hits": 4, "reference_words": 7, "hypothesis_words": 7, "edits": 3 }, "wer": 0.42857142857142855, "wer_percent": 42.857142857142854, "alignment": [ { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 3, "hypothesis_index": 3 }, { "op": "substitute", "reference": "no", "hypothesis": "beb", "reference_index": 4, "hypothesis_index": 4 }, { "op": "substitute", "reference": "de", "hypothesis": "bebop", "reference_index": 5, "hypothesis_index": 5 }, { "op": "substitute", "reference": "gusto", "hypothesis": "lee", "reference_index": 6, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.61568, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Happy", "emotion_confidence": 0.46374139189720154, "duration_seconds": 0.7340000000000089, "mos": 3.2603, "audio_variant": "cleaned", "original_transcript_raw": "Bueno", "original_transcript": "Bueno", "retranscribed_transcript": "Bueno.", "backend": "qwen", "emotion_analyzed_seconds": 0.734, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-100", "energy": { "value": 0.50390625, "bucket": "low" }, "audio_url": "audio/utterance-100.wav", "spectrogram_url": "spectrograms/utterance-100.png", "waveform": [ 0.19961, 0.20185, 0.11333, 0.10066, 0.08209, 0.05701, 0.09106, 0.06337, 0.03805, 0.04075, 0.03097, 0.12164, 0.07622, 0.20209, 0.18121, 0.16215, 0.39975, 0.14163, 0.39862, 0.19911, 0.42313, 0.28201, 0.36137, 0.42878, 0.26326, 0.46186, 0.17358, 0.442, 0.43378, 0.44833, 0.48901, 0.19986, 0.53408, 0.45469, 0.33453, 0.37675, 0.23253, 0.35491, 0.34004, 0.19115, 0.34189, 0.37408, 0.19272, 0.44062, 0.51397, 0.25498, 0.56753, 0.6262, 0.3447, 0.59278, 0.59754, 0.53679, 0.2354, 0.45262, 0.41045, 0.32692, 0.28923, 0.24751, 0.23234, 0.22208, 0.18628, 0.16271, 0.16801, 0.13469, 0.12558, 0.12585, 0.11162, 0.10161, 0.07756, 0.06857, 0.06647, 0.05551, 0.04292, 0.02205, 0.01956, 0.01391, 0.01425, 0.01399, 0.01241, 0.00868, 0.00435, 0.00789, 0.00758, 0.00572, 0.0059, 0.00653, 0.00555, 0.00368, 0.00422, 0.00404, 0.00327, 0.00419, 0.00214, 0.00217, 0.00183, 0.00117, 0.00167, 0.00124, 0.00162, 0.00144, 0.00078, 0.00039, 0.00021, 0.00025, 0.00022, 4e-05, 5e-05, 4e-05, 4e-05, 4e-05, 3e-05, 4e-05, 3e-05, 3e-05, 4e-05, 3e-05, 4e-05, 3e-05, 3e-05, 2e-05, 2e-05, 2e-05, 2e-05, 1e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 1e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 1e-05, 2e-05, 1e-05, 1e-05, 2e-05, 2e-05, 1e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 1e-05, 1e-05, 1e-05, 1e-05, 2e-05, 1e-05, 1e-05, 2e-05, 2e-05, 1e-05, 2e-05, 0.00011, 0.00017, 0.00019, 0.00015, 0.00089, 0.01443, 0.02735, 0.05293, 0.0712, 0.06041, 0.05786, 0.04868, 0.23438, 0.23033, 0.19996, 0.20069, 0.22097 ], "comparison": { "original": "Bueno", "retranscribed": "Bueno.", "reference_tokens": [ "bueno" ], "hypothesis_tokens": [ "bueno" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 1, "reference_words": 1, "hypothesis_words": 1, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "bueno", "hypothesis": "bueno", "reference_index": 0, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.6262, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Happy", "emotion_confidence": 0.5435288548469543, "duration_seconds": 3.3279999999999745, "mos": 3.2927, "audio_variant": "cleaned", "original_transcript_raw": "Todo esto es tuyo, Jack. ", "original_transcript": "Todo esto es tuyo, Jack.", "retranscribed_transcript": "Todo esto es tuyo, Jack.", "backend": "qwen", "emotion_analyzed_seconds": 3.328, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-101", "energy": { "value": 0.50390625, "bucket": "low" }, "audio_url": "audio/utterance-101.wav", "spectrogram_url": "spectrograms/utterance-101.png", "waveform": [ 0.16644, 0.07906, 0.04097, 0.00071, 0.00052, 0.00036, 0.00026, 0.00019, 0.00014, 0.0001, 7e-05, 6e-05, 5e-05, 4e-05, 3e-05, 3e-05, 3e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 1e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 3e-05, 2e-05, 2e-05, 2e-05, 2e-05, 4e-05, 3e-05, 4e-05, 7e-05, 9e-05, 0.00011, 0.0001, 0.00012, 0.00014, 0.00015, 0.00019, 0.00012, 0.00013, 0.00015, 0.00022, 0.00027, 0.00043, 0.00061, 0.00042, 0.00059, 0.00092, 0.00076, 0.00069, 0.00096, 0.00068, 0.00086, 0.00077, 0.00073, 0.0008, 0.00105, 0.00104, 0.00092, 0.00098, 0.00088, 0.0008, 0.00083, 0.0008, 0.00099, 0.00075, 0.00079, 0.00062, 0.00056, 0.00059, 0.0004, 0.00059, 0.0007, 0.00057, 0.08802, 0.50061, 0.43471, 0.43813, 0.43938, 0.44954, 0.36593, 0.12527, 0.34935, 0.36473, 0.3563, 0.36434, 0.30522, 0.38554, 0.40332, 0.47743, 0.44905, 0.41999, 0.31953, 0.09021, 0.03742, 0.01842, 0.00613, 0.00082, 0.01123, 0.02358, 0.27566, 0.26664, 0.31249, 0.32715, 0.27685, 0.15367, 0.03889, 0.02871, 0.01366, 0.0009, 0.00056, 0.00046, 0.00063, 0.05446, 0.07393, 0.18219, 0.17529, 0.15772, 0.1785, 0.17683, 0.15257, 0.12228, 0.05521, 0.0284, 0.02237, 0.09034, 0.12627, 0.27704, 0.28974, 0.28256, 0.26514, 0.14399, 0.08444, 0.04522, 0.05411, 0.10891, 0.22232, 0.35035, 0.32416, 0.27826, 0.34851, 0.37242, 0.33035, 0.27873, 0.29968, 0.21288, 0.15619, 0.01015, 0.00094, 0.00073, 0.0006, 0.05636, 0.03063, 0.01366, 0.01227, 0.00995, 0.00683, 0.00497, 0.00281, 0.00216, 0.00147, 0.00152, 0.0339, 0.08347, 0.13383 ], "comparison": { "original": "Todo esto es tuyo, Jack.", "retranscribed": "Todo esto es tuyo, Jack.", "reference_tokens": [ "todo", "esto", "es", "tuyo", "jack" ], "hypothesis_tokens": [ "todo", "esto", "es", "tuyo", "jack" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "todo", "hypothesis": "todo", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "esto", "hypothesis": "esto", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "es", "hypothesis": "es", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "tuyo", "hypothesis": "tuyo", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "jack", "hypothesis": "jack", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.50061, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Happy", "emotion_confidence": 0.49329420924186707, "duration_seconds": 2.714, "mos": 3.8657, "audio_variant": "cleaned", "original_transcript_raw": "Con su carita preciosa. ", "original_transcript": "Con su carita preciosa.", "retranscribed_transcript": "Con su carita preciosa.", "backend": "qwen", "emotion_analyzed_seconds": 2.714, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-102", "energy": { "value": 0.462890625, "bucket": "low" }, "audio_url": "audio/utterance-102.wav", "spectrogram_url": "spectrograms/utterance-102.png", "waveform": [ 0.60535, 0.26052, 0.39298, 0.59437, 0.58993, 0.52014, 0.51451, 0.53892, 0.47985, 0.44616, 0.33764, 0.31121, 0.27919, 0.25442, 0.25965, 0.22591, 0.24861, 0.27021, 0.29434, 0.32776, 0.33566, 0.32772, 0.34523, 0.36171, 0.36628, 0.36007, 0.35629, 0.34056, 0.32044, 0.30961, 0.31997, 0.29332, 0.17698, 0.09345, 0.06091, 0.08281, 0.11778, 0.10679, 0.18815, 0.18162, 0.27761, 0.35174, 0.40046, 0.39519, 0.37043, 0.35506, 0.29416, 0.13888, 0.09193, 0.06486, 0.04717, 0.14837, 0.1875, 0.16366, 0.40958, 0.43437, 0.53818, 0.74745, 0.82639, 0.81591, 0.81331, 0.77143, 0.51361, 0.38064, 0.13546, 0.27003, 0.4996, 0.4882, 0.50797, 0.40216, 0.32107, 0.29541, 0.2657, 0.25838, 0.27648, 0.27089, 0.26575, 0.27044, 0.27599, 0.27053, 0.28933, 0.28767, 0.28719, 0.28169, 0.26221, 0.28393, 0.30437, 0.2899, 0.30475, 0.29925, 0.32694, 0.32271, 0.3157, 0.33496, 0.32265, 0.24476, 0.0774, 0.03216, 0.00542, 0.00167, 0.00102, 0.00054, 0.00032, 0.00053, 0.08472, 0.39897, 0.51743, 0.67818, 0.65589, 0.63607, 0.54649, 0.35643, 0.05375, 0.01539, 0.00389, 0.00077, 0.00085, 0.00209, 0.16681, 0.31964, 0.41777, 0.09349, 0.37238, 0.43417, 0.39911, 0.34359, 0.28701, 0.23176, 0.1765, 0.08523, 0.10389, 0.14087, 0.14774, 0.20325, 0.14875, 0.13612, 0.07385, 0.24604, 0.248, 0.26256, 0.3016, 0.30669, 0.30592, 0.34833, 0.41106, 0.38874, 0.36315, 0.35164, 0.33309, 0.29317, 0.24221, 0.08619, 0.07709, 0.11805, 0.12392, 0.10671, 0.11142, 0.07982, 0.11498, 0.20488, 0.26284, 0.26776, 0.25422, 0.22437, 0.21925, 0.18786, 0.19426, 0.16669, 0.14507, 0.13271, 0.11824, 0.094, 0.10533, 0.10999, 0.10503, 0.09151, 0.08468, 0.06341, 0.05155, 0.06328 ], "comparison": { "original": "Con su carita preciosa.", "retranscribed": "Con su carita preciosa.", "reference_tokens": [ "con", "su", "carita", "preciosa" ], "hypothesis_tokens": [ "con", "su", "carita", "preciosa" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 4, "reference_words": 4, "hypothesis_words": 4, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "con", "hypothesis": "con", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "su", "hypothesis": "su", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "carita", "hypothesis": "carita", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "preciosa", "hypothesis": "preciosa", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.82639, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Happy", "emotion_confidence": 0.7018643617630005, "duration_seconds": 15.153, "mos": 3.0655, "audio_variant": "original", "original_transcript_raw": "Si nos divertimos mucho, bueno, en lo particular me divertí mucho aquí con José tratando de agarrar las, las canastas y pues logramos recuperar el equipo, no cayó al agua y pues eso habla bien también ahí de, de, de que es un buen equipo y lo vamos a poder usar para el próximo reto. ", "original_transcript": "Si nos divertimos mucho, bueno, en lo particular me divertí mucho aquí con José tratando de agarrar las, las canastas y pues logramos recuperar el equipo, no cayó al agua y pues eso habla bien también ahí de, de, de que es un buen equipo y lo vamos a poder usar para el próximo reto.", "retranscribed_transcript": "sí nos divertimos mucho bueno en lo particular me divertí mucho aquí con José tratando de agarrar las las canastas y pues logramos recuperar el el equipo nunca iba el agua y pues eso habla bien también ahí de de que es un buen equipo y lo vamos a poder usar para el próximo reto", "backend": "qwen", "emotion_analyzed_seconds": 15.153, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-103", "energy": { "value": 0.5546875, "bucket": "medium" }, "audio_url": "audio/utterance-103.wav", "spectrogram_url": "spectrograms/utterance-103.png", "waveform": [ 0.15062, 0.17263, 0.27377, 0.11113, 0.21978, 0.34217, 0.41548, 0.4242, 0.38966, 0.20876, 0.17489, 0.13603, 0.01168, 0.03232, 0.15228, 0.41619, 0.40974, 0.25877, 0.5547, 0.19149, 0.27352, 0.33887, 0.19907, 0.19937, 0.30217, 0.27482, 0.38105, 0.26353, 0.22306, 0.23385, 0.19064, 0.19236, 0.18658, 0.14058, 0.15932, 0.45366, 0.45443, 0.24886, 0.26018, 0.24644, 0.24329, 0.17544, 0.14449, 0.13572, 0.17594, 0.19173, 0.03247, 0.08541, 0.10197, 0.10146, 0.07167, 0.03192, 0.19874, 0.33848, 0.32342, 0.13736, 0.31262, 0.06525, 0.48326, 0.24913, 0.27025, 0.38122, 0.22822, 0.19898, 0.25463, 0.20531, 0.34639, 0.19664, 0.02636, 0.2191, 0.19889, 0.03588, 0.22229, 0.26886, 0.25589, 0.03109, 0.27261, 0.2225, 0.01235, 0.00828, 0.01075, 0.00951, 0.0119, 0.01056, 0.02487, 0.23217, 0.29693, 0.29331, 0.29209, 0.10074, 0.32448, 0.06561, 0.34011, 0.3522, 0.53004, 0.27028, 0.23297, 0.10331, 0.14561, 0.38095, 0.41964, 0.49972, 0.43825, 0.40501, 0.14285, 0.10859, 0.14309, 0.16957, 0.1531, 0.11148, 0.10985, 0.19353, 0.202, 0.13588, 0.13176, 0.35877, 0.29785, 0.37814, 0.51676, 0.52644, 0.28782, 0.31228, 0.18477, 0.10223, 0.11139, 0.11861, 0.08414, 0.20092, 0.29987, 0.21818, 0.22292, 0.18552, 0.06135, 0.14658, 0.09425, 0.10984, 0.13871, 0.14718, 0.12057, 0.13834, 0.14317, 0.11175, 0.11085, 0.12459, 0.09843, 0.09566, 0.12648, 0.12423, 0.08743, 0.07926, 0.25342, 0.23539, 0.12615, 0.10647, 0.03827, 0.13781, 0.12944, 0.09072, 0.14392, 0.14247, 0.27025, 0.20785, 0.1046, 0.14499, 0.07232, 0.12513, 0.13131, 0.10702, 0.19489, 0.16931, 0.19172, 0.15385, 0.053, 0.12001, 0.07255, 0.05982, 0.07339, 0.06677, 0.1004, 0.01656 ], "comparison": { "original": "Si nos divertimos mucho, bueno, en lo particular me divertí mucho aquí con José tratando de agarrar las, las canastas y pues logramos recuperar el equipo, no cayó al agua y pues eso habla bien también ahí de, de, de que es un buen equipo y lo vamos a poder usar para el próximo reto.", "retranscribed": "sí nos divertimos mucho bueno en lo particular me divertí mucho aquí con José tratando de agarrar las las canastas y pues logramos recuperar el el equipo nunca iba el agua y pues eso habla bien también ahí de de que es un buen equipo y lo vamos a poder usar para el próximo reto", "reference_tokens": [ "si", "nos", "divertimos", "mucho", "bueno", "en", "lo", "particular", "me", "divertí", "mucho", "aquí", "con", "josé", "tratando", "de", "agarrar", "las", "las", "canastas", "y", "pues", "logramos", "recuperar", "el", "equipo", "no", "cayó", "al", "agua", "y", "pues", "eso", "habla", "bien", "también", "ahí", "de", "de", "de", "que", "es", "un", "buen", "equipo", "y", "lo", "vamos", "a", "poder", "usar", "para", "el", "próximo", "reto" ], "hypothesis_tokens": [ "sí", "nos", "divertimos", "mucho", "bueno", "en", "lo", "particular", "me", "divertí", "mucho", "aquí", "con", "josé", "tratando", "de", "agarrar", "las", "las", "canastas", "y", "pues", "logramos", "recuperar", "el", "el", "equipo", "nunca", "iba", "el", "agua", "y", "pues", "eso", "habla", "bien", "también", "ahí", "de", "de", "que", "es", "un", "buen", "equipo", "y", "lo", "vamos", "a", "poder", "usar", "para", "el", "próximo", "reto" ], "counts": { "substitutions": 4, "deletions": 1, "insertions": 1, "hits": 50, "reference_words": 55, "hypothesis_words": 55, "edits": 6 }, "wer": 0.10909090909090909, "wer_percent": 10.909090909090908, "alignment": [ { "op": "substitute", "reference": "si", "hypothesis": "sí", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "nos", "hypothesis": "nos", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "divertimos", "hypothesis": "divertimos", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "mucho", "hypothesis": "mucho", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "bueno", "hypothesis": "bueno", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "en", "hypothesis": "en", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "lo", "hypothesis": "lo", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "particular", "hypothesis": "particular", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "divertí", "hypothesis": "divertí", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "mucho", "hypothesis": "mucho", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "aquí", "hypothesis": "aquí", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "con", "hypothesis": "con", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "josé", "hypothesis": "josé", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "tratando", "hypothesis": "tratando", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "agarrar", "hypothesis": "agarrar", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "las", "hypothesis": "las", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "las", "hypothesis": "las", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "canastas", "hypothesis": "canastas", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "pues", "hypothesis": "pues", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "logramos", "hypothesis": "logramos", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "recuperar", "hypothesis": "recuperar", "reference_index": 23, "hypothesis_index": 23 }, { "op": "insert", "reference": null, "hypothesis": "el", "reference_index": null, "hypothesis_index": 24 }, { "op": "equal", "reference": "el", "hypothesis": "el", "reference_index": 24, "hypothesis_index": 25 }, { "op": "equal", "reference": "equipo", "hypothesis": "equipo", "reference_index": 25, "hypothesis_index": 26 }, { "op": "substitute", "reference": "no", "hypothesis": "nunca", "reference_index": 26, "hypothesis_index": 27 }, { "op": "substitute", "reference": "cayó", "hypothesis": "iba", "reference_index": 27, "hypothesis_index": 28 }, { "op": "substitute", "reference": "al", "hypothesis": "el", "reference_index": 28, "hypothesis_index": 29 }, { "op": "equal", "reference": "agua", "hypothesis": "agua", "reference_index": 29, "hypothesis_index": 30 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 30, "hypothesis_index": 31 }, { "op": "equal", "reference": "pues", "hypothesis": "pues", "reference_index": 31, "hypothesis_index": 32 }, { "op": "equal", "reference": "eso", "hypothesis": "eso", "reference_index": 32, "hypothesis_index": 33 }, { "op": "equal", "reference": "habla", "hypothesis": "habla", "reference_index": 33, "hypothesis_index": 34 }, { "op": "equal", "reference": "bien", "hypothesis": "bien", "reference_index": 34, "hypothesis_index": 35 }, { "op": "equal", "reference": "también", "hypothesis": "también", "reference_index": 35, "hypothesis_index": 36 }, { "op": "equal", "reference": "ahí", "hypothesis": "ahí", "reference_index": 36, "hypothesis_index": 37 }, { "op": "delete", "reference": "de", "hypothesis": null, "reference_index": 37, "hypothesis_index": null }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 38, "hypothesis_index": 38 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 39, "hypothesis_index": 39 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 40, "hypothesis_index": 40 }, { "op": "equal", "reference": "es", "hypothesis": "es", "reference_index": 41, "hypothesis_index": 41 }, { "op": "equal", "reference": "un", "hypothesis": "un", "reference_index": 42, "hypothesis_index": 42 }, { "op": "equal", "reference": "buen", "hypothesis": "buen", "reference_index": 43, "hypothesis_index": 43 }, { "op": "equal", "reference": "equipo", "hypothesis": "equipo", "reference_index": 44, "hypothesis_index": 44 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 45, "hypothesis_index": 45 }, { "op": "equal", "reference": "lo", "hypothesis": "lo", "reference_index": 46, "hypothesis_index": 46 }, { "op": "equal", "reference": "vamos", "hypothesis": "vamos", "reference_index": 47, "hypothesis_index": 47 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 48, "hypothesis_index": 48 }, { "op": "equal", "reference": "poder", "hypothesis": "poder", "reference_index": 49, "hypothesis_index": 49 }, { "op": "equal", "reference": "usar", "hypothesis": "usar", "reference_index": 50, "hypothesis_index": 50 }, { "op": "equal", "reference": "para", "hypothesis": "para", "reference_index": 51, "hypothesis_index": 51 }, { "op": "equal", "reference": "el", "hypothesis": "el", "reference_index": 52, "hypothesis_index": 52 }, { "op": "equal", "reference": "próximo", "hypothesis": "próximo", "reference_index": 53, "hypothesis_index": 53 }, { "op": "equal", "reference": "reto", "hypothesis": "reto", "reference_index": 54, "hypothesis_index": 54 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.5547, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Happy", "emotion_confidence": 0.6530459523200989, "duration_seconds": 11.757000000000001, "mos": 3.6584, "audio_variant": "cleaned", "original_transcript_raw": "San Lorenzo de Tanicuchí un fuerte abrazo a todas las familias tanicuchenses, a los empresarios, a los comerciantes, a todas las familias que hacen de esta parroquia grande y productiva. ", "original_transcript": "San Lorenzo de Tanicuchí un fuerte abrazo a todas las familias tanicuchenses, a los empresarios, a los comerciantes, a todas las familias que hacen de esta parroquia grande y productiva.", "retranscribed_transcript": "San Lorenzo de Tanicuchí. Un fuerte abrazo a todas las familias tanicuchenses, a los empresarios, a los comerciantes, a todas las familias que hacen de esta parroquia grande y productiva.", "backend": "qwen", "emotion_analyzed_seconds": 11.757, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-104", "energy": { "value": 0.55078125, "bucket": "medium" }, "audio_url": "audio/utterance-104.wav", "spectrogram_url": "spectrograms/utterance-104.png", "waveform": [ 0.23014, 0.33611, 0.22045, 0.12772, 0.26738, 0.47523, 0.45255, 0.47291, 0.4499, 0.24439, 0.14827, 0.23709, 0.2835, 0.38721, 0.20038, 0.32107, 0.16282, 0.16896, 0.09206, 0.23251, 0.12004, 0.29614, 0.21887, 0.16806, 0.01643, 0.00027, 0.11865, 0.30077, 0.28704, 0.06554, 0.72478, 0.67845, 0.1622, 0.31701, 0.73045, 0.59551, 0.61318, 0.65616, 0.65867, 0.13759, 0.40813, 0.47168, 0.43389, 0.56364, 0.47507, 0.41642, 0.43139, 0.35894, 0.47624, 0.37543, 0.2076, 0.40019, 0.31808, 0.39021, 0.38928, 0.4399, 0.54181, 0.07792, 0.48599, 0.38715, 0.37757, 0.05699, 0.31136, 0.12209, 0.39934, 0.42722, 0.36704, 0.12392, 0.31676, 0.1688, 0.00786, 0.01803, 0.02032, 0.015, 0.43103, 0.47316, 0.43072, 0.37999, 0.54906, 0.37402, 0.21191, 0.37757, 0.30462, 0.14298, 0.58369, 0.61452, 0.59752, 0.26153, 0.31764, 0.21741, 0.02918, 0.00553, 0.00183, 0.37652, 0.37026, 0.32182, 0.1279, 0.223, 0.5398, 0.39742, 0.399, 0.26278, 0.10239, 0.42263, 0.40103, 0.39236, 0.19728, 0.10389, 0.28992, 0.12574, 0.03257, 0.00023, 2e-05, 2e-05, 0.0018, 0.00663, 0.41774, 0.22181, 0.72669, 0.57796, 0.46854, 0.60054, 0.68488, 0.04919, 0.48854, 0.45076, 0.38951, 0.34744, 0.33369, 0.53519, 0.59616, 0.44511, 0.21949, 0.03251, 0.00172, 0.00072, 0.00018, 0.00016, 0.05215, 0.56742, 0.54496, 0.29356, 0.62201, 0.35352, 0.22681, 0.40539, 0.18503, 0.52489, 0.4214, 0.13286, 0.47994, 0.4872, 0.61095, 0.68411, 0.05062, 0.51972, 0.46524, 0.15947, 0.00748, 0.00305, 0.00925, 0.4475, 0.59999, 0.46341, 0.40701, 0.36785, 0.28936, 0.31114, 0.45234, 0.35443, 0.37602, 0.01443, 0.42282, 0.39272, 0.34775, 0.17717, 0.01007, 0.00019, 1e-05, 0.07861 ], "comparison": { "original": "San Lorenzo de Tanicuchí un fuerte abrazo a todas las familias tanicuchenses, a los empresarios, a los comerciantes, a todas las familias que hacen de esta parroquia grande y productiva.", "retranscribed": "San Lorenzo de Tanicuchí. Un fuerte abrazo a todas las familias tanicuchenses, a los empresarios, a los comerciantes, a todas las familias que hacen de esta parroquia grande y productiva.", "reference_tokens": [ "san", "lorenzo", "de", "tanicuchí", "un", "fuerte", "abrazo", "a", "todas", "las", "familias", "tanicuchenses", "a", "los", "empresarios", "a", "los", "comerciantes", "a", "todas", "las", "familias", "que", "hacen", "de", "esta", "parroquia", "grande", "y", "productiva" ], "hypothesis_tokens": [ "san", "lorenzo", "de", "tanicuchí", "un", "fuerte", "abrazo", "a", "todas", "las", "familias", "tanicuchenses", "a", "los", "empresarios", "a", "los", "comerciantes", "a", "todas", "las", "familias", "que", "hacen", "de", "esta", "parroquia", "grande", "y", "productiva" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 30, "reference_words": 30, "hypothesis_words": 30, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "san", "hypothesis": "san", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "lorenzo", "hypothesis": "lorenzo", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "tanicuchí", "hypothesis": "tanicuchí", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "un", "hypothesis": "un", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "fuerte", "hypothesis": "fuerte", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "abrazo", "hypothesis": "abrazo", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "todas", "hypothesis": "todas", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "las", "hypothesis": "las", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "familias", "hypothesis": "familias", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "tanicuchenses", "hypothesis": "tanicuchenses", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "los", "hypothesis": "los", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "empresarios", "hypothesis": "empresarios", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "los", "hypothesis": "los", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "comerciantes", "hypothesis": "comerciantes", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "todas", "hypothesis": "todas", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "las", "hypothesis": "las", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "familias", "hypothesis": "familias", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "hacen", "hypothesis": "hacen", "reference_index": 23, "hypothesis_index": 23 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 24, "hypothesis_index": 24 }, { "op": "equal", "reference": "esta", "hypothesis": "esta", "reference_index": 25, "hypothesis_index": 25 }, { "op": "equal", "reference": "parroquia", "hypothesis": "parroquia", "reference_index": 26, "hypothesis_index": 26 }, { "op": "equal", "reference": "grande", "hypothesis": "grande", "reference_index": 27, "hypothesis_index": 27 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 28, "hypothesis_index": 28 }, { "op": "equal", "reference": "productiva", "hypothesis": "productiva", "reference_index": 29, "hypothesis_index": 29 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.73045, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Happy", "emotion_confidence": 0.3238001763820648, "duration_seconds": 1.2970000000000255, "mos": 3.0957, "audio_variant": "cleaned", "original_transcript_raw": "Абруха с копазитова", "original_transcript": "Абруха с копазитова", "retranscribed_transcript": "La bruja es capaz de todo.", "backend": "qwen", "emotion_analyzed_seconds": 1.297, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-105", "energy": { "value": 0.578125, "bucket": "medium" }, "audio_url": "audio/utterance-105.wav", "spectrogram_url": "spectrograms/utterance-105.png", "waveform": [ 0.00873, 0.10995, 0.12634, 0.12489, 0.14761, 0.16859, 0.0975, 0.15014, 0.1038, 0.11866, 0.08928, 0.09494, 0.08916, 0.05653, 0.04443, 0.02997, 0.03808, 0.0231, 0.05192, 0.03024, 0.07045, 0.04982, 0.14037, 0.06821, 0.12164, 0.03164, 0.04482, 0.04694, 0.11795, 0.19107, 0.19352, 0.24588, 0.11251, 0.21845, 0.21498, 0.11279, 0.22508, 0.13701, 0.20155, 0.18583, 0.10895, 0.17772, 0.09234, 0.10883, 0.06647, 0.04947, 0.06435, 0.06992, 0.03518, 0.03743, 0.03456, 0.04136, 0.04236, 0.03651, 0.02342, 0.013, 0.09539, 0.20485, 0.22388, 0.16937, 0.23847, 0.1504, 0.17412, 0.11077, 0.08498, 0.06572, 0.05363, 0.04862, 0.05112, 0.05087, 0.01754, 0.00511, 0.00181, 0.00073, 0.00511, 0.04948, 0.0352, 0.01318, 0.06276, 0.13337, 0.25343, 0.15659, 0.26438, 0.09191, 0.06058, 0.04124, 0.02108, 0.01656, 0.00796, 0.00241, 0.00127, 0.00046, 0.03201, 0.01285, 0.01602, 0.16269, 0.19164, 0.26437, 0.29922, 0.20292, 0.2913, 0.12624, 0.29647, 0.26948, 0.13484, 0.17022, 0.09383, 0.0634, 0.06393, 0.0478, 0.04195, 0.05338, 0.03746, 0.1099, 0.08877, 0.14088, 0.13244, 0.14438, 0.13756, 0.14782, 0.08213, 0.05674, 0.01574, 0.01146, 0.01139, 0.00433, 0.00253, 0.00071, 0.00483, 0.00267, 0.02129, 0.03397, 0.01294, 0.06096, 0.04917, 0.17091, 0.11776, 0.16873, 0.0796, 0.13106, 0.06448, 0.13663, 0.05833, 0.13759, 0.07699, 0.09719, 0.06068, 0.08231, 0.04782, 0.06222, 0.06742, 0.06575, 0.05362, 0.03798, 0.06382, 0.02745, 0.06457, 0.03323, 0.04552, 0.03259, 0.0227, 0.01862, 0.01929, 0.01484, 0.01645, 0.01807, 0.01218, 0.01186, 0.00872, 0.00937, 0.00798, 0.00816, 0.00363, 0.00855, 0.00645, 0.00559, 0.00653, 0.00903, 0.00997, 0.00803 ], "comparison": { "original": "Абруха с копазитова", "retranscribed": "La bruja es capaz de todo.", "reference_tokens": [ "абруха", "с", "копазитова" ], "hypothesis_tokens": [ "la", "bruja", "es", "capaz", "de", "todo" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 3, "hits": 0, "reference_words": 3, "hypothesis_words": 6, "edits": 6 }, "wer": 2.0, "wer_percent": 200.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "la", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "bruja", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "es", "reference_index": null, "hypothesis_index": 2 }, { "op": "substitute", "reference": "абруха", "hypothesis": "capaz", "reference_index": 0, "hypothesis_index": 3 }, { "op": "substitute", "reference": "с", "hypothesis": "de", "reference_index": 1, "hypothesis_index": 4 }, { "op": "substitute", "reference": "копазитова", "hypothesis": "todo", "reference_index": 2, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.29922, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Happy", "emotion_confidence": 0.65439772605896, "duration_seconds": 10.408999999999992, "mos": 3.45, "audio_variant": "cleaned", "original_transcript_raw": "muy bien y ahora hablaremos un poco sobre Fanput. Él ha sido dos veces campeón mundial este año él va a ser el hombre más fuerte del mundo si es que gana este torneo", "original_transcript": "muy bien y ahora hablaremos un poco sobre Fanput. Él ha sido dos veces campeón mundial este año él va a ser el hombre más fuerte del mundo si es que gana este torneo", "retranscribed_transcript": "Muy bien, y ahora hablaremos un poco sobre Famput. Él ha sido dos veces campeón mundial. Este año, él va a ser el hombre más fuerte del mundo si es que gana este torneo.", "backend": "qwen", "emotion_analyzed_seconds": 10.409, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-106", "energy": { "value": 0.69140625, "bucket": "high" }, "audio_url": "audio/utterance-106.wav", "spectrogram_url": "spectrograms/utterance-106.png", "waveform": [ 0.37592, 0.3112, 0.2192, 0.25012, 0.20159, 0.2847, 0.31312, 0.3708, 0.313, 0.21859, 0.08067, 0.24331, 0.36649, 0.53056, 0.47695, 0.38654, 0.47402, 0.54701, 0.33471, 0.38504, 0.40989, 0.44729, 0.33442, 0.46175, 0.31713, 0.28894, 0.26368, 0.24386, 0.13896, 0.08797, 0.38402, 0.33346, 0.06737, 0.13815, 0.39962, 0.30743, 0.15896, 0.30051, 0.24213, 0.33809, 0.18786, 0.01114, 0.46257, 0.44467, 0.52184, 0.29651, 0.08215, 0.06318, 0.14335, 0.28932, 0.20804, 0.11441, 0.22529, 0.30036, 0.53925, 0.65661, 0.10405, 0.22208, 0.20115, 0.44086, 0.3329, 0.4559, 0.52393, 0.40629, 0.17133, 0.08285, 0.16819, 0.16475, 0.13078, 0.2245, 0.20436, 0.14418, 0.02021, 0.49862, 0.3718, 0.1126, 0.02382, 0.42729, 0.51009, 0.28476, 0.11613, 0.17075, 0.17822, 0.14625, 0.27954, 0.49603, 0.45274, 0.42688, 0.07645, 0.02369, 0.00119, 0.00158, 0.00137, 0.00155, 0.00142, 0.00146, 0.00123, 0.00091, 0.01435, 0.24182, 0.09046, 0.57469, 0.73385, 0.48409, 0.43838, 0.12267, 0.23671, 0.38426, 0.33686, 0.08894, 0.00388, 0.0031, 0.0021, 0.04568, 0.28426, 0.18751, 0.57928, 0.4737, 0.57789, 0.10052, 0.45491, 0.39679, 0.31826, 0.29827, 0.40752, 0.26245, 0.36582, 0.40232, 0.24468, 0.4295, 0.47221, 0.05438, 0.01021, 0.3506, 0.51939, 0.14664, 0.22869, 0.30305, 0.58061, 0.40562, 0.14847, 0.24356, 0.24419, 0.16654, 0.29347, 0.43079, 0.34342, 0.0694, 0.00225, 0.04742, 0.12381, 0.18999, 0.41371, 0.54965, 0.26054, 0.11946, 0.46024, 0.47303, 0.39563, 0.49305, 0.40545, 0.4212, 0.44832, 0.35947, 0.44138, 0.2347, 0.0519, 0.31439, 0.37251, 0.20785, 0.59874, 0.45153, 0.15965, 0.42387, 0.52123, 0.50363, 0.46993, 0.25762, 0.26046, 0.442 ], "comparison": { "original": "muy bien y ahora hablaremos un poco sobre Fanput. Él ha sido dos veces campeón mundial este año él va a ser el hombre más fuerte del mundo si es que gana este torneo", "retranscribed": "Muy bien, y ahora hablaremos un poco sobre Famput. Él ha sido dos veces campeón mundial. Este año, él va a ser el hombre más fuerte del mundo si es que gana este torneo.", "reference_tokens": [ "muy", "bien", "y", "ahora", "hablaremos", "un", "poco", "sobre", "fanput", "él", "ha", "sido", "dos", "veces", "campeón", "mundial", "este", "año", "él", "va", "a", "ser", "el", "hombre", "más", "fuerte", "del", "mundo", "si", "es", "que", "gana", "este", "torneo" ], "hypothesis_tokens": [ "muy", "bien", "y", "ahora", "hablaremos", "un", "poco", "sobre", "famput", "él", "ha", "sido", "dos", "veces", "campeón", "mundial", "este", "año", "él", "va", "a", "ser", "el", "hombre", "más", "fuerte", "del", "mundo", "si", "es", "que", "gana", "este", "torneo" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 33, "reference_words": 34, "hypothesis_words": 34, "edits": 1 }, "wer": 0.029411764705882353, "wer_percent": 2.941176470588235, "alignment": [ { "op": "equal", "reference": "muy", "hypothesis": "muy", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "bien", "hypothesis": "bien", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "ahora", "hypothesis": "ahora", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "hablaremos", "hypothesis": "hablaremos", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "un", "hypothesis": "un", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "poco", "hypothesis": "poco", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "sobre", "hypothesis": "sobre", "reference_index": 7, "hypothesis_index": 7 }, { "op": "substitute", "reference": "fanput", "hypothesis": "famput", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "él", "hypothesis": "él", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "ha", "hypothesis": "ha", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "sido", "hypothesis": "sido", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "dos", "hypothesis": "dos", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "veces", "hypothesis": "veces", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "campeón", "hypothesis": "campeón", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "mundial", "hypothesis": "mundial", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "este", "hypothesis": "este", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "año", "hypothesis": "año", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "él", "hypothesis": "él", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "va", "hypothesis": "va", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "ser", "hypothesis": "ser", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "el", "hypothesis": "el", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "hombre", "hypothesis": "hombre", "reference_index": 23, "hypothesis_index": 23 }, { "op": "equal", "reference": "más", "hypothesis": "más", "reference_index": 24, "hypothesis_index": 24 }, { "op": "equal", "reference": "fuerte", "hypothesis": "fuerte", "reference_index": 25, "hypothesis_index": 25 }, { "op": "equal", "reference": "del", "hypothesis": "del", "reference_index": 26, "hypothesis_index": 26 }, { "op": "equal", "reference": "mundo", "hypothesis": "mundo", "reference_index": 27, "hypothesis_index": 27 }, { "op": "equal", "reference": "si", "hypothesis": "si", "reference_index": 28, "hypothesis_index": 28 }, { "op": "equal", "reference": "es", "hypothesis": "es", "reference_index": 29, "hypothesis_index": 29 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 30, "hypothesis_index": 30 }, { "op": "equal", "reference": "gana", "hypothesis": "gana", "reference_index": 31, "hypothesis_index": 31 }, { "op": "equal", "reference": "este", "hypothesis": "este", "reference_index": 32, "hypothesis_index": 32 }, { "op": "equal", "reference": "torneo", "hypothesis": "torneo", "reference_index": 33, "hypothesis_index": 33 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.73385, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Happy", "emotion_confidence": 0.6715822219848633, "duration_seconds": 3.2420000000000186, "mos": 2.835, "audio_variant": "cleaned", "original_transcript_raw": "Para tú estás vivo eres tu abuela. ", "original_transcript": "Para tú estás vivo eres tu abuela.", "retranscribed_transcript": "Papas parto estás vivo eres tu abuela", "backend": "qwen", "emotion_analyzed_seconds": 3.242, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-107", "energy": { "value": 0.859375, "bucket": "high" }, "audio_url": "audio/utterance-107.wav", "spectrogram_url": "spectrograms/utterance-107.png", "waveform": [ 0.12052, 0.14915, 0.39963, 0.44615, 0.35235, 0.30064, 0.28886, 0.28706, 0.24664, 0.3053, 0.30718, 0.34099, 0.30786, 0.30517, 0.00839, 0.00135, 0.00057, 0.00047, 0.02391, 0.1012, 0.36706, 0.36931, 0.35117, 0.22901, 0.13078, 0.0256, 0.01846, 0.01084, 0.00193, 0.00058, 0.00047, 0.01736, 0.34436, 0.4363, 0.43934, 0.40763, 0.19312, 0.09976, 0.09469, 0.00312, 0.00064, 0.00024, 0.00032, 0.02767, 0.32456, 0.34399, 0.19484, 0.25232, 0.26657, 0.2962, 0.30417, 0.35132, 0.37418, 0.3219, 0.33757, 0.30106, 0.22829, 0.04417, 0.02663, 0.0121, 0.00283, 0.01698, 0.22746, 0.32316, 0.4288, 0.39767, 0.34129, 0.30903, 0.03789, 0.01122, 0.01281, 0.00872, 0.00206, 0.00061, 0.0007, 0.0304, 0.10613, 0.13452, 0.1765, 0.14901, 0.11365, 0.11578, 0.14056, 0.17432, 0.33506, 0.12598, 0.00798, 0.01522, 0.27039, 0.31582, 0.32802, 0.36694, 0.35588, 0.34732, 0.30317, 0.31371, 0.3027, 0.16737, 0.15316, 0.09048, 0.07262, 0.03559, 0.01365, 0.00708, 0.00902, 0.01113, 0.12494, 0.19012, 0.26367, 0.33916, 0.31941, 0.33087, 0.3944, 0.3852, 0.36945, 0.19225, 0.25277, 0.35483, 0.39391, 0.43225, 0.3957, 0.37555, 0.30122, 0.2964, 0.16067, 0.05175, 0.03408, 0.01838, 0.00081, 0.00031, 0.00041, 0.04082, 0.17351, 0.17525, 0.18905, 0.16666, 0.16987, 0.2288, 0.34333, 0.39219, 0.38816, 0.44775, 0.47689, 0.49755, 0.5044, 0.38851, 0.29772, 0.20727, 0.08774, 0.07679, 0.17118, 0.25655, 0.33106, 0.36341, 0.38399, 0.31915, 0.41592, 0.4159, 0.42012, 0.39429, 0.3628, 0.19334, 0.218, 0.24938, 0.32026, 0.34949, 0.33411, 0.3451, 0.36511, 0.33517, 0.36628, 0.21797, 0.18457, 0.13072, 0.07189, 0.08335, 0.08179, 0.04957, 0.10026, 0.10167 ], "comparison": { "original": "Para tú estás vivo eres tu abuela.", "retranscribed": "Papas parto estás vivo eres tu abuela", "reference_tokens": [ "para", "tú", "estás", "vivo", "eres", "tu", "abuela" ], "hypothesis_tokens": [ "papas", "parto", "estás", "vivo", "eres", "tu", "abuela" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 7, "hypothesis_words": 7, "edits": 2 }, "wer": 0.2857142857142857, "wer_percent": 28.57142857142857, "alignment": [ { "op": "substitute", "reference": "para", "hypothesis": "papas", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "tú", "hypothesis": "parto", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "estás", "hypothesis": "estás", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "vivo", "hypothesis": "vivo", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "eres", "hypothesis": "eres", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "tu", "hypothesis": "tu", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "abuela", "hypothesis": "abuela", "reference_index": 6, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.5044, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Happy", "emotion_confidence": 0.6682033538818359, "duration_seconds": 6.280000000000001, "mos": 3.0438, "audio_variant": "cleaned", "original_transcript_raw": "Maya, dónde¿ estás otra vez lo mismo se ha vuelto a ir Maya", "original_transcript": "Maya, dónde¿ estás otra vez lo mismo se ha vuelto a ir Maya", "retranscribed_transcript": "Maya, dónde estás otra vez lo mismo se ha vuelto a ir Maya", "backend": "qwen", "emotion_analyzed_seconds": 6.28, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-108", "energy": { "value": 0.6953125, "bucket": "high" }, "audio_url": "audio/utterance-108.wav", "spectrogram_url": "spectrograms/utterance-108.png", "waveform": [ 0.02595, 0.10135, 0.12988, 0.44805, 0.54748, 0.61291, 0.37433, 0.4242, 0.29715, 0.40548, 0.36364, 0.31709, 0.24827, 0.30489, 0.2542, 0.18641, 0.08343, 0.29774, 0.30303, 0.2869, 0.28772, 0.09202, 0.00966, 0.00797, 0.24562, 0.2463, 0.40019, 0.40708, 0.39493, 0.38712, 0.34401, 0.33133, 0.31865, 0.18622, 0.04927, 0.04635, 0.01943, 0.00163, 0.00101, 0.00155, 0.00209, 0.00226, 0.00283, 0.00185, 0.00135, 0.00066, 0.0007, 0.00031, 0.00057, 0.0014, 0.10195, 0.19514, 0.25879, 0.29394, 0.04888, 0.0106, 0.12324, 0.35088, 0.50539, 0.46156, 0.32174, 0.17833, 0.21461, 0.16924, 0.14345, 0.07775, 0.20947, 0.31487, 0.31705, 0.22062, 0.19487, 0.27761, 0.3548, 0.37393, 0.29671, 0.15517, 0.06971, 0.11367, 0.13712, 0.16185, 0.06229, 0.02319, 0.24613, 0.3006, 0.34753, 0.41267, 0.10078, 0.28346, 0.33324, 0.27012, 0.21843, 0.06549, 0.01338, 0.1462, 0.24455, 0.4016, 0.51594, 0.46603, 0.22467, 0.23416, 0.22336, 0.20301, 0.24676, 0.16878, 0.15448, 0.15632, 0.16695, 0.20045, 0.21973, 0.18178, 0.14101, 0.09013, 0.02912, 0.00119, 0.00445, 0.00335, 0.00474, 0.003, 0.00182, 0.00102, 0.00092, 0.00061, 0.0005, 0.00076, 0.02275, 0.05393, 0.13824, 0.14689, 0.19461, 0.25453, 0.12733, 0.018, 0.00489, 0.00234, 0.00169, 0.0012, 0.00122, 0.00166, 0.00582, 0.03103, 0.06387, 0.08398, 0.08908, 0.09026, 0.08217, 0.0649, 0.0058, 0.00541, 0.00865, 0.00694, 0.00195, 0.00068, 0.00452, 0.10038, 0.32683, 0.3415, 0.35877, 0.3951, 0.25926, 0.21219, 0.19664, 0.23425, 0.30049, 0.30402, 0.36355, 0.36738, 0.37751, 0.34096, 0.29917, 0.27409, 0.25847, 0.26042, 0.05793, 0.03351, 0.01386, 0.00608, 0.00185, 0.00055, 0.01401, 0.04348 ], "comparison": { "original": "Maya, dónde¿ estás otra vez lo mismo se ha vuelto a ir Maya", "retranscribed": "Maya, dónde estás otra vez lo mismo se ha vuelto a ir Maya", "reference_tokens": [ "maya", "dónde", "estás", "otra", "vez", "lo", "mismo", "se", "ha", "vuelto", "a", "ir", "maya" ], "hypothesis_tokens": [ "maya", "dónde", "estás", "otra", "vez", "lo", "mismo", "se", "ha", "vuelto", "a", "ir", "maya" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 13, "reference_words": 13, "hypothesis_words": 13, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "maya", "hypothesis": "maya", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "dónde", "hypothesis": "dónde", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "estás", "hypothesis": "estás", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "otra", "hypothesis": "otra", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "vez", "hypothesis": "vez", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "lo", "hypothesis": "lo", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "mismo", "hypothesis": "mismo", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "se", "hypothesis": "se", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "ha", "hypothesis": "ha", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "vuelto", "hypothesis": "vuelto", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "ir", "hypothesis": "ir", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "maya", "hypothesis": "maya", "reference_index": 12, "hypothesis_index": 12 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.61291, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Neutral", "emotion_confidence": 0.7755677700042725, "duration_seconds": 10.323999999999998, "mos": 3.5162, "audio_variant": "cleaned", "original_transcript_raw": "Estados Unidos sobrepasó sus fronteras en todas las esferas la económica, la política y la humanitaria y se ha impuesto sobre otras naciones. ", "original_transcript": "Estados Unidos sobrepasó sus fronteras en todas las esferas la económica, la política y la humanitaria y se ha impuesto sobre otras naciones.", "retranscribed_transcript": "Estados Unidos sobrepasó sus fronteras en todas las esferas: la económica, la política y la humanitaria y se ha impuesto sobre otras naciones.", "backend": "qwen", "emotion_analyzed_seconds": 10.324, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-109", "energy": { "value": 0.490234375, "bucket": "low" }, "audio_url": "audio/utterance-109.wav", "spectrogram_url": "spectrograms/utterance-109.png", "waveform": [ 0.17689, 0.10821, 0.84272, 0.75956, 0.50415, 0.43766, 0.25265, 0.31918, 0.44908, 0.56758, 0.51614, 0.47556, 0.4165, 0.50456, 0.38866, 0.17416, 0.38105, 0.32268, 0.36643, 0.25412, 0.29144, 0.2206, 0.19428, 0.36025, 0.34959, 0.08492, 0.25503, 0.18951, 0.06572, 0.2697, 0.26762, 0.13387, 0.25407, 0.38332, 0.37329, 0.62815, 0.54783, 0.50545, 0.12326, 0.2811, 0.22611, 0.18362, 0.01503, 0.50953, 0.57815, 0.42658, 0.40102, 0.56267, 0.46647, 0.11571, 0.46414, 0.40139, 0.12586, 0.24858, 0.15474, 0.07182, 0.53387, 0.41518, 0.25216, 0.0973, 0.05182, 0.04355, 0.07578, 0.01843, 0.01543, 0.01136, 0.17907, 0.47379, 0.35426, 0.15544, 0.13218, 0.26781, 0.16945, 0.33197, 0.35889, 0.34296, 0.46954, 0.30902, 0.14874, 0.65468, 0.60812, 0.36324, 0.31618, 0.04634, 0.00604, 0.00648, 0.00585, 0.00594, 0.00418, 0.00346, 0.10293, 0.36583, 0.5212, 0.4129, 0.07317, 0.22894, 0.16066, 0.16064, 0.42433, 0.43003, 0.12847, 0.05799, 0.31336, 0.18485, 0.16051, 0.47148, 0.51101, 0.37946, 0.38492, 0.24607, 0.01509, 0.00577, 0.00489, 0.00235, 0.00145, 0.00122, 0.00077, 0.29277, 0.49376, 0.43073, 0.44443, 0.65436, 0.52894, 0.41317, 0.30416, 0.23833, 0.41503, 0.5229, 0.25725, 0.26374, 0.05114, 0.68866, 0.78278, 0.33938, 0.13917, 0.05896, 0.0787, 0.06948, 0.03741, 0.12224, 0.25919, 0.16719, 0.31503, 0.67518, 0.37739, 0.30419, 0.10697, 0.38561, 0.66746, 0.46549, 0.14206, 0.27371, 0.3838, 0.22185, 0.37046, 0.58694, 0.35799, 0.48502, 0.39156, 0.31465, 0.33476, 0.55771, 0.56143, 0.07645, 0.39312, 0.44341, 0.29737, 0.26706, 0.44289, 0.38833, 0.16409, 0.29347, 0.18427, 0.03366, 0.03045, 0.02624, 0.06689, 0.05059, 0.00275, 0.05516 ], "comparison": { "original": "Estados Unidos sobrepasó sus fronteras en todas las esferas la económica, la política y la humanitaria y se ha impuesto sobre otras naciones.", "retranscribed": "Estados Unidos sobrepasó sus fronteras en todas las esferas: la económica, la política y la humanitaria y se ha impuesto sobre otras naciones.", "reference_tokens": [ "estados", "unidos", "sobrepasó", "sus", "fronteras", "en", "todas", "las", "esferas", "la", "económica", "la", "política", "y", "la", "humanitaria", "y", "se", "ha", "impuesto", "sobre", "otras", "naciones" ], "hypothesis_tokens": [ "estados", "unidos", "sobrepasó", "sus", "fronteras", "en", "todas", "las", "esferas", "la", "económica", "la", "política", "y", "la", "humanitaria", "y", "se", "ha", "impuesto", "sobre", "otras", "naciones" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 23, "reference_words": 23, "hypothesis_words": 23, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "estados", "hypothesis": "estados", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "unidos", "hypothesis": "unidos", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "sobrepasó", "hypothesis": "sobrepasó", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "sus", "hypothesis": "sus", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "fronteras", "hypothesis": "fronteras", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "en", "hypothesis": "en", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "todas", "hypothesis": "todas", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "las", "hypothesis": "las", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "esferas", "hypothesis": "esferas", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "la", "hypothesis": "la", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "económica", "hypothesis": "económica", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "la", "hypothesis": "la", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "política", "hypothesis": "política", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "la", "hypothesis": "la", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "humanitaria", "hypothesis": "humanitaria", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "se", "hypothesis": "se", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "ha", "hypothesis": "ha", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "impuesto", "hypothesis": "impuesto", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "sobre", "hypothesis": "sobre", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "otras", "hypothesis": "otras", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "naciones", "hypothesis": "naciones", "reference_index": 22, "hypothesis_index": 22 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.84272, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Neutral", "emotion_confidence": 0.6689845323562622, "duration_seconds": 0.7680000000000007, "mos": 3.2385, "audio_variant": "original", "original_transcript_raw": "Бел", "original_transcript": "Бел", "retranscribed_transcript": "Bueno.", "backend": "qwen", "emotion_analyzed_seconds": 0.768, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-110", "energy": { "value": 0.48828125, "bucket": "low" }, "audio_url": "audio/utterance-110.wav", "spectrogram_url": "spectrograms/utterance-110.png", "waveform": [ 0.00695, 0.01242, 0.01291, 0.01381, 0.01289, 0.01912, 0.01867, 0.02445, 0.03571, 0.05824, 0.18113, 0.23724, 0.1577, 0.29652, 0.33063, 0.29564, 0.3308, 0.26147, 0.32347, 0.1756, 0.33022, 0.29512, 0.29079, 0.30861, 0.26819, 0.17189, 0.11187, 0.10256, 0.13655, 0.0438, 0.0547, 0.04248, 0.06194, 0.05941, 0.06104, 0.109, 0.07883, 0.13826, 0.14134, 0.32935, 0.29011, 0.3993, 0.42503, 0.34279, 0.40355, 0.36934, 0.40946, 0.4343, 0.49174, 0.49605, 0.29235, 0.52197, 0.34757, 0.31749, 0.20714, 0.42357, 0.24846, 0.31496, 0.1976, 0.2928, 0.21495, 0.22701, 0.13778, 0.11621, 0.10488, 0.09476, 0.05987, 0.08822, 0.07253, 0.06447, 0.06672, 0.07093, 0.08459, 0.10829, 0.17992, 0.18355, 0.29568, 0.15652, 0.20675, 0.2032, 0.16384, 0.13968, 0.20783, 0.13099, 0.18122, 0.14613, 0.15049, 0.13234, 0.15171, 0.16004, 0.19553, 0.1526, 0.09538, 0.1346, 0.12534, 0.13423, 0.157, 0.07914, 0.14501, 0.12087, 0.08803, 0.11936, 0.09508, 0.05249, 0.12792, 0.09646, 0.06719, 0.07299, 0.08836, 0.05218, 0.08602, 0.03106, 0.06122, 0.06831, 0.03015, 0.0352, 0.02715, 0.02892, 0.02128, 0.01355, 0.00817, 0.00964, 0.00635, 0.00828, 0.00836, 0.00823, 0.00597, 0.00511, 0.00373, 0.00782, 0.00978, 0.00393, 0.00845, 0.00451, 0.00508, 0.00728, 0.00925, 0.00744, 0.00655, 0.00481, 0.00958, 0.0099, 0.00879, 0.01212, 0.01303, 0.01053, 0.0066, 0.00626, 0.00667, 0.00872, 0.00697, 0.00765, 0.00848, 0.00504, 0.00899, 0.00734, 0.00828, 0.01082, 0.00344, 0.00713, 0.00435, 0.00863, 0.00583, 0.0036, 0.00755, 0.00647, 0.00589, 0.00479, 0.00823, 0.00666, 0.00839, 0.0078, 0.00908, 0.00954, 0.00491, 0.00462, 0.00986, 0.00982, 0.00993, 0.00627 ], "comparison": { "original": "Бел", "retranscribed": "Bueno.", "reference_tokens": [ "бел" ], "hypothesis_tokens": [ "bueno" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 0, "reference_words": 1, "hypothesis_words": 1, "edits": 1 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "substitute", "reference": "бел", "hypothesis": "bueno", "reference_index": 0, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.52197, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Neutral", "emotion_confidence": 0.6891503930091858, "duration_seconds": 1.757000000000005, "mos": 3.0502, "audio_variant": "cleaned", "original_transcript_raw": "Me¿ recuerda donde crecí, de hecho? ", "original_transcript": "Me¿ recuerda donde crecí, de hecho?", "retranscribed_transcript": "Me recuerda donde crecí de ellos.", "backend": "qwen", "emotion_analyzed_seconds": 1.757, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-111", "energy": { "value": 0.490234375, "bucket": "low" }, "audio_url": "audio/utterance-111.wav", "spectrogram_url": "spectrograms/utterance-111.png", "waveform": [ 0.06061, 0.05927, 0.03414, 0.03101, 0.21413, 0.24038, 0.24954, 0.37886, 0.4436, 0.41671, 0.48142, 0.55803, 0.36886, 0.11615, 0.33723, 0.36831, 0.32062, 0.19622, 0.40547, 0.57468, 0.50699, 0.50824, 0.46221, 0.4155, 0.30577, 0.1066, 0.05045, 0.01375, 0.00627, 0.00343, 0.00291, 0.2721, 0.0765, 0.11506, 0.25587, 0.31869, 0.34228, 0.4374, 0.48765, 0.4943, 0.5117, 0.47206, 0.49497, 0.4313, 0.13604, 0.25027, 0.34256, 0.15291, 0.12687, 0.10359, 0.1912, 0.31291, 0.4386, 0.4369, 0.51457, 0.5163, 0.49342, 0.42486, 0.38794, 0.31605, 0.14533, 0.10473, 0.0735, 0.15338, 0.21165, 0.27953, 0.27196, 0.30667, 0.31008, 0.34752, 0.33427, 0.34311, 0.28759, 0.33688, 0.31344, 0.31811, 0.29199, 0.25237, 0.18507, 0.06152, 0.17222, 0.28119, 0.20134, 0.23311, 0.22494, 0.16599, 0.03856, 0.01533, 0.00417, 0.0054, 0.1257, 0.04456, 0.05179, 0.12736, 0.08698, 0.03039, 0.04518, 0.13405, 0.16281, 0.16453, 0.15626, 0.16608, 0.13346, 0.10705, 0.09498, 0.06427, 0.04411, 0.0418, 0.04897, 0.0675, 0.06518, 0.05596, 0.0662, 0.10466, 0.06729, 0.05714, 0.05234, 0.11961, 0.2013, 0.24691, 0.3061, 0.29874, 0.30637, 0.2785, 0.25099, 0.24363, 0.1935, 0.0975, 0.05368, 0.02308, 0.01576, 0.02907, 0.06001, 0.17516, 0.23425, 0.25741, 0.22912, 0.23462, 0.2454, 0.21793, 0.19494, 0.19796, 0.18327, 0.16015, 0.18111, 0.16054, 0.17386, 0.16375, 0.18668, 0.16458, 0.17775, 0.15732, 0.14244, 0.13955, 0.14342, 0.14145, 0.12715, 0.11332, 0.09295, 0.08204, 0.05524, 0.02673, 0.00486, 0.00197, 0.00216, 0.0021, 0.00407, 0.01946, 0.05555, 0.10589, 0.09446, 0.08515, 0.03259, 0.02271, 0.02234, 0.03319, 0.09284, 0.08197, 0.11524, 0.12085 ], "comparison": { "original": "Me¿ recuerda donde crecí, de hecho?", "retranscribed": "Me recuerda donde crecí de ellos.", "reference_tokens": [ "me", "recuerda", "donde", "crecí", "de", "hecho" ], "hypothesis_tokens": [ "me", "recuerda", "donde", "crecí", "de", "ellos" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 6, "hypothesis_words": 6, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "recuerda", "hypothesis": "recuerda", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "donde", "hypothesis": "donde", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "crecí", "hypothesis": "crecí", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 4, "hypothesis_index": 4 }, { "op": "substitute", "reference": "hecho", "hypothesis": "ellos", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.57468, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Neutral", "emotion_confidence": 0.564490795135498, "duration_seconds": 2.695999999999998, "mos": 3.1414, "audio_variant": "cleaned", "original_transcript_raw": "Obras y servicios para los vecinos. ", "original_transcript": "Obras y servicios para los vecinos.", "retranscribed_transcript": "Sumamos obras y servicios para los vecinos.", "backend": "qwen", "emotion_analyzed_seconds": 2.696, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-112", "energy": { "value": 0.52734375, "bucket": "medium" }, "audio_url": "audio/utterance-112.wav", "spectrogram_url": "spectrograms/utterance-112.png", "waveform": [ 0.31389, 0.21918, 0.10845, 0.05222, 0.26529, 0.39595, 0.39305, 0.30991, 0.23707, 0.14933, 0.16089, 0.17059, 0.1823, 0.29884, 0.33737, 0.41591, 0.38819, 0.54352, 0.48489, 0.43295, 0.50305, 0.19063, 0.20949, 0.19855, 0.18918, 0.19812, 0.25283, 0.24374, 0.24416, 0.22962, 0.13247, 0.07816, 0.08891, 0.09798, 0.10627, 0.08007, 0.07808, 0.13365, 0.07561, 0.44303, 0.4722, 0.5297, 0.53487, 0.46333, 0.45338, 0.34136, 0.34302, 0.36059, 0.43794, 0.35278, 0.27011, 0.26455, 0.2615, 0.33658, 0.2895, 0.1922, 0.16697, 0.09708, 0.1052, 0.1034, 0.08386, 0.06998, 0.15844, 0.22636, 0.17671, 0.16988, 0.14999, 0.09641, 0.09188, 0.10346, 0.07676, 0.11378, 0.27097, 0.39917, 0.36213, 0.34382, 0.2607, 0.24384, 0.09758, 0.18134, 0.2344, 0.19347, 0.1255, 0.15176, 0.21215, 0.30051, 0.32693, 0.3268, 0.35273, 0.22254, 0.15472, 0.11811, 0.13775, 0.13501, 0.12294, 0.10861, 0.06801, 0.26711, 0.39916, 0.42702, 0.25305, 0.22923, 0.18006, 0.09971, 0.01527, 0.00382, 0.00123, 0.00087, 0.00115, 0.10616, 0.3622, 0.48875, 0.43933, 0.3425, 0.11643, 0.29244, 0.28173, 0.24672, 0.22998, 0.1915, 0.23486, 0.23582, 0.2588, 0.16713, 0.19324, 0.17904, 0.07875, 0.07803, 0.05153, 0.10804, 0.17652, 0.22994, 0.20872, 0.16699, 0.09173, 0.09, 0.10563, 0.11961, 0.09023, 0.1003, 0.138, 0.12167, 0.26783, 0.24477, 0.24541, 0.24302, 0.29771, 0.29446, 0.18405, 0.17469, 0.16426, 0.16719, 0.16918, 0.16322, 0.12535, 0.10162, 0.16606, 0.16234, 0.15333, 0.12931, 0.09121, 0.0326, 0.03568, 0.04121, 0.02783, 0.02949, 0.03828, 0.03199, 0.03017, 0.02637, 0.02101, 0.01224, 0.01084, 0.00375, 0.00155, 0.00088, 0.00946, 0.08558, 0.15507, 0.17743 ], "comparison": { "original": "Obras y servicios para los vecinos.", "retranscribed": "Sumamos obras y servicios para los vecinos.", "reference_tokens": [ "obras", "y", "servicios", "para", "los", "vecinos" ], "hypothesis_tokens": [ "sumamos", "obras", "y", "servicios", "para", "los", "vecinos" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 6, "reference_words": 6, "hypothesis_words": 7, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "sumamos", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "obras", "hypothesis": "obras", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "servicios", "hypothesis": "servicios", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "para", "hypothesis": "para", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "los", "hypothesis": "los", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "vecinos", "hypothesis": "vecinos", "reference_index": 5, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.54352, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Neutral", "emotion_confidence": 0.611051619052887, "duration_seconds": 2.608312000000012, "mos": 3.6323, "audio_variant": "cleaned", "original_transcript_raw": "Se dio cuenta que le faltaba. ", "original_transcript": "Se dio cuenta que le faltaba.", "retranscribed_transcript": "Se dio cuenta que le faltaba compa.", "backend": "qwen", "emotion_analyzed_seconds": 2.6083125, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-113", "energy": { "value": 0.5390625, "bucket": "medium" }, "audio_url": "audio/utterance-113.wav", "spectrogram_url": "spectrograms/utterance-113.png", "waveform": [ 0.1506, 0.07745, 0.03009, 0.00761, 0.00364, 0.01153, 0.02563, 0.03088, 0.03484, 0.03835, 0.11578, 0.30016, 0.30353, 0.31049, 0.30948, 0.37366, 0.36901, 0.11245, 0.09129, 0.14629, 0.24369, 0.2993, 0.34549, 0.5676, 0.5849, 0.24589, 0.28159, 0.25169, 0.30459, 0.2646, 0.06807, 0.01871, 0.00309, 0.00061, 0.00046, 0.00051, 0.0223, 0.12492, 0.24883, 0.42256, 0.56433, 0.54503, 0.25222, 0.24642, 0.29519, 0.32348, 0.3167, 0.33297, 0.11773, 0.11757, 0.11836, 0.09533, 0.04533, 0.01343, 0.00271, 0.00073, 0.00044, 0.04304, 0.27523, 0.34238, 0.52393, 0.40169, 0.40248, 0.46717, 0.48402, 0.46641, 0.45101, 0.43073, 0.33887, 0.26121, 0.05728, 0.0232, 0.00709, 0.003, 0.00097, 0.00052, 0.00046, 0.00037, 0.00073, 0.00055, 0.00041, 0.00033, 0.00037, 0.00055, 0.00041, 0.00058, 0.00038, 0.00037, 0.00037, 0.00043, 0.0005, 0.00031, 0.00045, 0.00025, 0.00035, 0.00029, 0.00034, 0.00024, 0.00029, 0.00029, 0.00015, 0.0002, 0.0002, 0.00029, 0.05886, 0.10468, 0.29018, 0.271, 0.2827, 0.32456, 0.22318, 0.16891, 0.15364, 0.34323, 0.35264, 0.24383, 0.33893, 0.35764, 0.17171, 0.03161, 0.01448, 0.01246, 0.01351, 0.20148, 0.50177, 0.51868, 0.31214, 0.28326, 0.21557, 0.17134, 0.09062, 0.0648, 0.02355, 0.00783, 0.00193, 0.00051, 0.05497, 0.31312, 0.4977, 0.6387, 0.51665, 0.45519, 0.40509, 0.4092, 0.39087, 0.09919, 0.13383, 0.19347, 0.50017, 0.35709, 0.45966, 0.41835, 0.30474, 0.20539, 0.11308, 0.05357, 0.031, 0.00461, 0.00096, 0.00035, 0.00093, 0.06925, 0.16906, 0.37614, 0.38829, 0.3757, 0.31741, 0.3019, 0.29927, 0.17241, 0.09689, 0.09439, 0.08668, 0.04535, 0.01744, 0.00499, 0.00071, 0.00042, 0.00353, 0.23075 ], "comparison": { "original": "Se dio cuenta que le faltaba.", "retranscribed": "Se dio cuenta que le faltaba compa.", "reference_tokens": [ "se", "dio", "cuenta", "que", "le", "faltaba" ], "hypothesis_tokens": [ "se", "dio", "cuenta", "que", "le", "faltaba", "compa" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 6, "reference_words": 6, "hypothesis_words": 7, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "equal", "reference": "se", "hypothesis": "se", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "dio", "hypothesis": "dio", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "cuenta", "hypothesis": "cuenta", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "le", "hypothesis": "le", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "faltaba", "hypothesis": "faltaba", "reference_index": 5, "hypothesis_index": 5 }, { "op": "insert", "reference": null, "hypothesis": "compa", "reference_index": null, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.6387, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Neutral", "emotion_confidence": 0.7357089519500732, "duration_seconds": 2.9350000000000023, "mos": 3.375, "audio_variant": "original", "original_transcript_raw": "sé qué hacer, quiero hacer lo correcto y eso es", "original_transcript": "sé qué hacer, quiero hacer lo correcto y eso es", "retranscribed_transcript": "no sé qué hacer quiero hacerlo correcto y eso es", "backend": "qwen", "emotion_analyzed_seconds": 2.935, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-114", "energy": { "value": 0.5234375, "bucket": "medium" }, "audio_url": "audio/utterance-114.wav", "spectrogram_url": "spectrograms/utterance-114.png", "waveform": [ 0.11773, 0.19052, 0.22269, 0.23506, 0.22279, 0.21861, 0.23804, 0.25914, 0.27118, 0.28768, 0.26758, 0.23188, 0.13703, 0.04497, 0.07042, 0.12888, 0.12923, 0.13226, 0.13635, 0.13118, 0.22705, 0.34076, 0.25107, 0.22603, 0.04742, 0.01573, 0.01372, 0.00945, 0.01049, 0.09291, 0.03171, 0.10635, 0.14773, 0.10725, 0.10377, 0.13421, 0.11163, 0.10345, 0.03531, 0.03639, 0.07218, 0.13863, 0.1742, 0.14308, 0.10678, 0.06499, 0.11803, 0.14243, 0.15598, 0.11519, 0.13255, 0.15178, 0.14202, 0.15037, 0.10946, 0.06965, 0.0179, 0.02905, 0.10145, 0.09338, 0.02295, 0.0507, 0.02386, 0.01813, 0.01214, 0.00996, 0.01802, 0.01606, 0.0168, 0.01106, 0.05937, 0.15216, 0.2904, 0.32105, 0.31915, 0.28953, 0.28873, 0.30066, 0.27243, 0.20991, 0.26167, 0.26808, 0.27813, 0.3251, 0.33072, 0.35675, 0.34161, 0.19725, 0.06752, 0.15499, 0.11723, 0.1085, 0.16338, 0.11719, 0.28731, 0.37066, 0.37426, 0.33628, 0.03186, 0.03039, 0.0809, 0.1964, 0.21834, 0.20132, 0.35856, 0.38505, 0.29711, 0.03444, 0.0226, 0.01807, 0.06293, 0.23015, 0.38222, 0.36611, 0.22172, 0.10898, 0.1613, 0.06318, 0.18294, 0.26299, 0.3079, 0.29013, 0.22192, 0.12322, 0.01989, 0.01646, 0.01281, 0.00984, 0.00989, 0.04464, 0.15367, 0.19984, 0.12875, 0.14645, 0.13517, 0.11438, 0.09925, 0.09647, 0.10833, 0.12188, 0.14596, 0.25779, 0.23734, 0.12077, 0.08885, 0.12873, 0.12707, 0.13559, 0.0404, 0.08248, 0.29196, 0.31504, 0.30416, 0.27252, 0.25004, 0.24834, 0.2223, 0.23265, 0.26507, 0.24782, 0.23892, 0.23214, 0.20599, 0.19894, 0.1193, 0.11335, 0.11174, 0.12687, 0.11553, 0.11772, 0.08774, 0.06368, 0.02367, 0.00905, 0.01124, 0.01259, 0.0095, 0.01192, 0.01545, 0.01429 ], "comparison": { "original": "sé qué hacer, quiero hacer lo correcto y eso es", "retranscribed": "no sé qué hacer quiero hacerlo correcto y eso es", "reference_tokens": [ "sé", "qué", "hacer", "quiero", "hacer", "lo", "correcto", "y", "eso", "es" ], "hypothesis_tokens": [ "no", "sé", "qué", "hacer", "quiero", "hacerlo", "correcto", "y", "eso", "es" ], "counts": { "substitutions": 1, "deletions": 1, "insertions": 1, "hits": 8, "reference_words": 10, "hypothesis_words": 10, "edits": 3 }, "wer": 0.3, "wer_percent": 30.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "no", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "sé", "hypothesis": "sé", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "qué", "hypothesis": "qué", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "hacer", "hypothesis": "hacer", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "quiero", "hypothesis": "quiero", "reference_index": 3, "hypothesis_index": 4 }, { "op": "delete", "reference": "hacer", "hypothesis": null, "reference_index": 4, "hypothesis_index": null }, { "op": "substitute", "reference": "lo", "hypothesis": "hacerlo", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "correcto", "hypothesis": "correcto", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "eso", "hypothesis": "eso", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "es", "hypothesis": "es", "reference_index": 9, "hypothesis_index": 9 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.38505, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Neutral", "emotion_confidence": 0.5701993107795715, "duration_seconds": 0.7669999999999959, "mos": 3.4211, "audio_variant": "cleaned", "original_transcript_raw": "Señor Toyoda. ", "original_transcript": "Señor Toyoda.", "retranscribed_transcript": "Señor Toyoda.", "backend": "qwen", "emotion_analyzed_seconds": 0.767, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-115", "energy": { "value": 0.6015625, "bucket": "high" }, "audio_url": "audio/utterance-115.wav", "spectrogram_url": "spectrograms/utterance-115.png", "waveform": [ 0.08116, 0.13373, 0.09234, 0.07661, 0.0363, 0.06356, 0.03484, 0.03591, 0.0177, 0.02688, 0.02541, 0.02716, 0.03194, 0.02708, 0.034, 0.0766, 0.17362, 0.27107, 0.19403, 0.2611, 0.25585, 0.21591, 0.26601, 0.25182, 0.26011, 0.18915, 0.1152, 0.1412, 0.13642, 0.2084, 0.23721, 0.17086, 0.23126, 0.24269, 0.24123, 0.2525, 0.24269, 0.22654, 0.20557, 0.22782, 0.24693, 0.16045, 0.30084, 0.30764, 0.34702, 0.244, 0.36744, 0.36087, 0.37895, 0.39533, 0.41546, 0.48019, 0.29778, 0.52836, 0.54454, 0.5237, 0.35507, 0.49296, 0.2367, 0.06336, 0.06357, 0.06781, 0.08528, 0.09128, 0.04049, 0.0378, 0.02272, 0.00885, 0.00715, 0.00673, 0.00392, 0.00429, 0.00175, 0.00276, 0.00324, 0.07118, 0.12169, 0.06701, 0.25827, 0.37283, 0.26984, 0.50417, 0.46242, 0.30668, 0.34718, 0.44197, 0.18168, 0.41211, 0.48929, 0.36397, 0.42464, 0.17186, 0.40509, 0.14292, 0.12871, 0.04142, 0.09752, 0.09244, 0.10113, 0.06826, 0.09939, 0.05958, 0.09893, 0.07947, 0.14137, 0.10353, 0.16941, 0.16977, 0.41306, 0.2396, 0.53573, 0.35633, 0.51359, 0.3677, 0.29005, 0.41103, 0.30357, 0.43316, 0.32225, 0.46224, 0.36635, 0.46003, 0.45141, 0.4096, 0.36487, 0.29202, 0.22857, 0.12229, 0.16518, 0.19984, 0.10745, 0.2834, 0.15372, 0.33212, 0.20884, 0.33766, 0.22834, 0.36389, 0.30335, 0.33061, 0.22235, 0.26679, 0.18936, 0.24423, 0.14442, 0.19569, 0.06575, 0.1606, 0.06529, 0.14381, 0.09158, 0.09114, 0.07847, 0.06901, 0.05771, 0.05198, 0.02498, 0.01792, 0.02054, 0.01627, 0.0137, 0.011, 0.00668, 0.00655, 0.00223, 0.0022, 0.00224, 0.00144, 0.00071, 0.00117, 0.00175, 0.00268, 0.00509, 0.0103, 0.00692, 0.00662, 0.00562, 0.01325, 0.00774, 0.00961 ], "comparison": { "original": "Señor Toyoda.", "retranscribed": "Señor Toyoda.", "reference_tokens": [ "señor", "toyoda" ], "hypothesis_tokens": [ "señor", "toyoda" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 2, "hypothesis_words": 2, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "señor", "hypothesis": "señor", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "toyoda", "hypothesis": "toyoda", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.54454, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Neutral", "emotion_confidence": 0.2739233672618866, "duration_seconds": 0.6650000000000205, "mos": 3.1589, "audio_variant": "cleaned", "original_transcript_raw": "머이자 이랄바", "original_transcript": "머이자 이랄바", "retranscribed_transcript": "Voy a ir al bay.", "backend": "qwen", "emotion_analyzed_seconds": 0.665, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-116", "energy": { "value": 0.61328125, "bucket": "high" }, "audio_url": "audio/utterance-116.wav", "spectrogram_url": "spectrograms/utterance-116.png", "waveform": [ 0.11205, 0.11572, 0.13677, 0.13406, 0.12861, 0.13015, 0.0983, 0.11131, 0.1145, 0.09739, 0.0879, 0.09417, 0.07574, 0.06352, 0.0709, 0.07478, 0.08434, 0.08354, 0.07557, 0.06873, 0.06706, 0.07184, 0.05924, 0.06013, 0.05787, 0.04841, 0.03966, 0.02885, 0.02344, 0.02329, 0.01766, 0.02012, 0.02108, 0.02133, 0.01423, 0.01628, 0.01427, 0.0156, 0.01529, 0.00945, 0.00899, 0.01001, 0.04076, 0.08111, 0.09372, 0.10154, 0.10071, 0.11191, 0.11025, 0.10594, 0.09576, 0.06566, 0.09695, 0.0969, 0.08341, 0.09185, 0.08856, 0.07635, 0.06992, 0.06549, 0.0649, 0.06603, 0.06067, 0.05229, 0.04883, 0.04783, 0.05133, 0.0424, 0.04845, 0.05391, 0.03222, 0.04766, 0.05098, 0.04802, 0.02949, 0.04352, 0.04547, 0.04071, 0.02986, 0.04577, 0.04738, 0.04942, 0.03387, 0.04069, 0.03825, 0.03118, 0.02518, 0.02579, 0.01606, 0.01656, 0.01706, 0.02228, 0.0313, 0.0571, 0.04122, 0.05664, 0.06321, 0.05805, 0.06527, 0.08034, 0.05436, 0.04934, 0.06572, 0.05863, 0.04223, 0.06537, 0.06708, 0.04354, 0.05831, 0.03751, 0.02368, 0.0243, 0.02783, 0.02648, 0.02476, 0.0283, 0.02583, 0.02247, 0.02427, 0.02142, 0.02098, 0.01962, 0.0186, 0.01277, 0.01249, 0.0074, 0.00636, 0.0036, 0.00342, 0.00259, 0.00176, 0.00137, 0.00121, 0.00094, 0.00096, 0.00125, 0.00193, 0.00273, 0.00687, 0.01235, 0.0298, 0.02833, 0.04869, 0.04986, 0.04771, 0.05055, 0.03665, 0.0602, 0.05031, 0.03828, 0.04283, 0.04097, 0.03971, 0.05076, 0.07208, 0.07969, 0.04154, 0.04028, 0.04615, 0.03517, 0.03388, 0.0419, 0.04024, 0.03054, 0.0395, 0.02616, 0.03132, 0.01924, 0.02426, 0.02024, 0.02204, 0.01895, 0.01757, 0.01932, 0.02015, 0.02067, 0.01736, 0.02051, 0.02042, 0.01926 ], "comparison": { "original": "머이자 이랄바", "retranscribed": "Voy a ir al bay.", "reference_tokens": [ "머이자", "이랄바" ], "hypothesis_tokens": [ "voy", "a", "ir", "al", "bay" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 3, "hits": 0, "reference_words": 2, "hypothesis_words": 5, "edits": 5 }, "wer": 2.5, "wer_percent": 250.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "voy", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "a", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "ir", "reference_index": null, "hypothesis_index": 2 }, { "op": "substitute", "reference": "머이자", "hypothesis": "al", "reference_index": 0, "hypothesis_index": 3 }, { "op": "substitute", "reference": "이랄바", "hypothesis": "bay", "reference_index": 1, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.13677, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Neutral", "emotion_confidence": 0.6213462948799133, "duration_seconds": 11.757999999999996, "mos": 3.267, "audio_variant": "cleaned", "original_transcript_raw": "cinco punto dos millones de metros cuadrados de malla vial y espacio público intervenidos. Completamos esta noche. Es un esfuerzo de Idu, Unidad de Mantenimiento Vial y las Alcaldías Locales. ", "original_transcript": "cinco punto dos millones de metros cuadrados de malla vial y espacio público intervenidos. Completamos esta noche. Es un esfuerzo de Idu, Unidad de Mantenimiento Vial y las Alcaldías Locales.", "retranscribed_transcript": "5.2 millones de metros cuadrados de malla vial y espacio público intervenidos completamos esta noche. Es un esfuerzo de Idu Unidad de Mantenimiento Vial y las alcaldías locales.", "backend": "qwen", "emotion_analyzed_seconds": 11.758, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-117", "energy": { "value": 0.6171875, "bucket": "high" }, "audio_url": "audio/utterance-117.wav", "spectrogram_url": "spectrograms/utterance-117.png", "waveform": [ 0.17427, 0.25824, 0.32543, 0.21727, 0.07932, 0.62832, 0.50238, 0.14872, 0.19781, 0.1204, 0.4897, 0.37516, 0.49127, 0.10049, 0.22964, 0.17643, 0.479, 0.27994, 0.3482, 0.16124, 0.29904, 0.3329, 0.34926, 0.06386, 0.32964, 0.34182, 0.0878, 0.21815, 0.52704, 0.30887, 0.33962, 0.4796, 0.46493, 0.35805, 0.22528, 0.30937, 0.0881, 0.39479, 0.18766, 0.02557, 0.04519, 0.30825, 0.49601, 0.50438, 0.26099, 0.35574, 0.29098, 0.19898, 0.43295, 0.38397, 0.18295, 0.36436, 0.1119, 0.28064, 0.32896, 0.20686, 0.4374, 0.20741, 0.2369, 0.21342, 0.2279, 0.1829, 0.22089, 0.26251, 0.34645, 0.25797, 0.24031, 0.23982, 0.26575, 0.07193, 0.32959, 0.26504, 0.09299, 0.33232, 0.04797, 0.29582, 0.25295, 0.23185, 0.17132, 0.01485, 0.00212, 0.00151, 0.0009, 0.00048, 0.16623, 0.4678, 0.47939, 0.14399, 0.40544, 0.38862, 0.39744, 0.39018, 0.1973, 0.08109, 0.05896, 0.01037, 0.00044, 0.00053, 0.00078, 0.0009, 0.00074, 0.00058, 0.11462, 0.16246, 0.26151, 0.24842, 0.33966, 0.44057, 0.06117, 0.44055, 0.42868, 0.15537, 0.50838, 0.48237, 0.10827, 0.27905, 0.30401, 0.29841, 0.25925, 0.21132, 0.21647, 0.20317, 0.14241, 0.04076, 0.14632, 0.14525, 0.30425, 0.35585, 0.3957, 0.32881, 0.29558, 0.24642, 0.2729, 0.23868, 0.28114, 0.22282, 0.06725, 0.34466, 0.41471, 0.58573, 0.57028, 0.34483, 0.13245, 0.02084, 0.00068, 0.00076, 0.00046, 0.0005, 0.03409, 0.21465, 0.44379, 0.57478, 0.09687, 0.41573, 0.22901, 0.04738, 0.44171, 0.39865, 0.14615, 0.29049, 0.44903, 0.29255, 0.08391, 0.33598, 0.22616, 0.03295, 0.47513, 0.48097, 0.12469, 0.0867, 0.02754, 0.01835, 0.01109, 0.00038, 0.00024, 7e-05, 2e-05, 2e-05, 1e-05, 0.11793 ], "comparison": { "original": "cinco punto dos millones de metros cuadrados de malla vial y espacio público intervenidos. Completamos esta noche. Es un esfuerzo de Idu, Unidad de Mantenimiento Vial y las Alcaldías Locales.", "retranscribed": "5.2 millones de metros cuadrados de malla vial y espacio público intervenidos completamos esta noche. Es un esfuerzo de Idu Unidad de Mantenimiento Vial y las alcaldías locales.", "reference_tokens": [ "cinco", "punto", "dos", "millones", "de", "metros", "cuadrados", "de", "malla", "vial", "y", "espacio", "público", "intervenidos", "completamos", "esta", "noche", "es", "un", "esfuerzo", "de", "idu", "unidad", "de", "mantenimiento", "vial", "y", "las", "alcaldías", "locales" ], "hypothesis_tokens": [ "5", "2", "millones", "de", "metros", "cuadrados", "de", "malla", "vial", "y", "espacio", "público", "intervenidos", "completamos", "esta", "noche", "es", "un", "esfuerzo", "de", "idu", "unidad", "de", "mantenimiento", "vial", "y", "las", "alcaldías", "locales" ], "counts": { "substitutions": 2, "deletions": 1, "insertions": 0, "hits": 27, "reference_words": 30, "hypothesis_words": 29, "edits": 3 }, "wer": 0.1, "wer_percent": 10.0, "alignment": [ { "op": "delete", "reference": "cinco", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "substitute", "reference": "punto", "hypothesis": "5", "reference_index": 1, "hypothesis_index": 0 }, { "op": "substitute", "reference": "dos", "hypothesis": "2", "reference_index": 2, "hypothesis_index": 1 }, { "op": "equal", "reference": "millones", "hypothesis": "millones", "reference_index": 3, "hypothesis_index": 2 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 4, "hypothesis_index": 3 }, { "op": "equal", "reference": "metros", "hypothesis": "metros", "reference_index": 5, "hypothesis_index": 4 }, { "op": "equal", "reference": "cuadrados", "hypothesis": "cuadrados", "reference_index": 6, "hypothesis_index": 5 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 7, "hypothesis_index": 6 }, { "op": "equal", "reference": "malla", "hypothesis": "malla", "reference_index": 8, "hypothesis_index": 7 }, { "op": "equal", "reference": "vial", "hypothesis": "vial", "reference_index": 9, "hypothesis_index": 8 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 10, "hypothesis_index": 9 }, { "op": "equal", "reference": "espacio", "hypothesis": "espacio", "reference_index": 11, "hypothesis_index": 10 }, { "op": "equal", "reference": "público", "hypothesis": "público", "reference_index": 12, "hypothesis_index": 11 }, { "op": "equal", "reference": "intervenidos", "hypothesis": "intervenidos", "reference_index": 13, "hypothesis_index": 12 }, { "op": "equal", "reference": "completamos", "hypothesis": "completamos", "reference_index": 14, "hypothesis_index": 13 }, { "op": "equal", "reference": "esta", "hypothesis": "esta", "reference_index": 15, "hypothesis_index": 14 }, { "op": "equal", "reference": "noche", "hypothesis": "noche", "reference_index": 16, "hypothesis_index": 15 }, { "op": "equal", "reference": "es", "hypothesis": "es", "reference_index": 17, "hypothesis_index": 16 }, { "op": "equal", "reference": "un", "hypothesis": "un", "reference_index": 18, "hypothesis_index": 17 }, { "op": "equal", "reference": "esfuerzo", "hypothesis": "esfuerzo", "reference_index": 19, "hypothesis_index": 18 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 20, "hypothesis_index": 19 }, { "op": "equal", "reference": "idu", "hypothesis": "idu", "reference_index": 21, "hypothesis_index": 20 }, { "op": "equal", "reference": "unidad", "hypothesis": "unidad", "reference_index": 22, "hypothesis_index": 21 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 23, "hypothesis_index": 22 }, { "op": "equal", "reference": "mantenimiento", "hypothesis": "mantenimiento", "reference_index": 24, "hypothesis_index": 23 }, { "op": "equal", "reference": "vial", "hypothesis": "vial", "reference_index": 25, "hypothesis_index": 24 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 26, "hypothesis_index": 25 }, { "op": "equal", "reference": "las", "hypothesis": "las", "reference_index": 27, "hypothesis_index": 26 }, { "op": "equal", "reference": "alcaldías", "hypothesis": "alcaldías", "reference_index": 28, "hypothesis_index": 27 }, { "op": "equal", "reference": "locales", "hypothesis": "locales", "reference_index": 29, "hypothesis_index": 28 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.62832, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Sad", "emotion_confidence": 0.4672008454799652, "duration_seconds": 7.048, "mos": 3.521, "audio_variant": "original", "original_transcript_raw": "en lo peor de la fiebre. Escuché una voz y creí que me decía que el caminante nos llevaría allá. Creí que la voz venía de padre. ", "original_transcript": "en lo peor de la fiebre. Escuché una voz y creí que me decía que el caminante nos llevaría allá. Creí que la voz venía de padre.", "retranscribed_transcript": "En lo peor de la fiebre escuché una voz y creí que me decía que el caminante nos llevaría allá. Creí que la voz venía de padre.", "backend": "qwen", "emotion_analyzed_seconds": 7.048, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-118", "energy": { "value": 0.515625, "bucket": "low" }, "audio_url": "audio/utterance-118.wav", "spectrogram_url": "spectrograms/utterance-118.png", "waveform": [ 0.301, 0.26854, 0.25006, 0.23191, 0.18534, 0.0349, 0.2187, 0.2517, 0.22676, 0.26833, 0.18073, 0.15155, 0.24626, 0.22646, 0.21085, 0.17333, 0.20011, 0.12096, 0.07907, 0.08093, 0.10622, 0.15189, 0.1406, 0.06409, 0.16145, 0.1519, 0.13601, 0.14384, 0.1583, 0.15287, 0.1006, 0.08052, 0.13729, 0.02657, 0.23487, 0.15694, 0.20471, 0.15069, 0.14829, 0.15507, 0.1609, 0.0738, 0.23315, 0.25248, 0.15289, 0.15806, 0.18678, 0.1384, 0.09473, 0.23236, 0.02655, 0.18859, 0.33238, 0.20845, 0.25645, 0.21682, 0.15803, 0.14564, 0.1065, 0.14607, 0.14526, 0.11011, 0.01945, 0.01348, 0.20391, 0.17903, 0.17169, 0.16172, 0.15531, 0.17373, 0.19593, 0.16543, 0.02575, 0.01919, 0.01706, 0.0144, 0.01046, 0.02104, 0.01006, 0.01672, 0.01682, 0.01333, 0.01758, 0.02958, 0.28624, 0.32236, 0.36925, 0.24736, 0.12844, 0.28399, 0.15143, 0.10894, 0.14055, 0.16447, 0.33514, 0.18551, 0.16012, 0.02138, 0.29691, 0.33487, 0.25781, 0.05811, 0.25133, 0.20711, 0.1195, 0.20924, 0.17833, 0.14579, 0.20182, 0.23385, 0.15206, 0.04434, 0.26906, 0.25889, 0.27522, 0.23918, 0.21101, 0.35353, 0.24473, 0.37722, 0.24598, 0.08963, 0.07692, 0.1222, 0.14331, 0.13309, 0.09411, 0.08575, 0.13476, 0.05586, 0.04959, 0.03454, 0.02568, 0.01406, 0.01528, 0.01495, 0.01893, 0.01232, 0.01508, 0.01706, 0.15347, 0.15259, 0.3305, 0.28175, 0.28908, 0.04423, 0.23823, 0.33005, 0.27575, 0.13334, 0.13661, 0.04586, 0.32568, 0.31248, 0.12223, 0.09115, 0.08345, 0.05376, 0.28138, 0.15161, 0.14309, 0.15411, 0.17298, 0.19536, 0.16018, 0.06534, 0.2269, 0.139, 0.01804, 0.01942, 0.31684, 0.51363, 0.27556, 0.08219, 0.14053, 0.07393, 0.04957, 0.03597, 0.0234, 0.02185 ], "comparison": { "original": "en lo peor de la fiebre. Escuché una voz y creí que me decía que el caminante nos llevaría allá. Creí que la voz venía de padre.", "retranscribed": "En lo peor de la fiebre escuché una voz y creí que me decía que el caminante nos llevaría allá. Creí que la voz venía de padre.", "reference_tokens": [ "en", "lo", "peor", "de", "la", "fiebre", "escuché", "una", "voz", "y", "creí", "que", "me", "decía", "que", "el", "caminante", "nos", "llevaría", "allá", "creí", "que", "la", "voz", "venía", "de", "padre" ], "hypothesis_tokens": [ "en", "lo", "peor", "de", "la", "fiebre", "escuché", "una", "voz", "y", "creí", "que", "me", "decía", "que", "el", "caminante", "nos", "llevaría", "allá", "creí", "que", "la", "voz", "venía", "de", "padre" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 27, "reference_words": 27, "hypothesis_words": 27, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "en", "hypothesis": "en", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "lo", "hypothesis": "lo", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "peor", "hypothesis": "peor", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "la", "hypothesis": "la", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "fiebre", "hypothesis": "fiebre", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "escuché", "hypothesis": "escuché", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "una", "hypothesis": "una", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "voz", "hypothesis": "voz", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "creí", "hypothesis": "creí", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "decía", "hypothesis": "decía", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "el", "hypothesis": "el", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "caminante", "hypothesis": "caminante", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "nos", "hypothesis": "nos", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "llevaría", "hypothesis": "llevaría", "reference_index": 18, "hypothesis_index": 18 }, { "op": "equal", "reference": "allá", "hypothesis": "allá", "reference_index": 19, "hypothesis_index": 19 }, { "op": "equal", "reference": "creí", "hypothesis": "creí", "reference_index": 20, "hypothesis_index": 20 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 21, "hypothesis_index": 21 }, { "op": "equal", "reference": "la", "hypothesis": "la", "reference_index": 22, "hypothesis_index": 22 }, { "op": "equal", "reference": "voz", "hypothesis": "voz", "reference_index": 23, "hypothesis_index": 23 }, { "op": "equal", "reference": "venía", "hypothesis": "venía", "reference_index": 24, "hypothesis_index": 24 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 25, "hypothesis_index": 25 }, { "op": "equal", "reference": "padre", "hypothesis": "padre", "reference_index": 26, "hypothesis_index": 26 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.51363, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Sad", "emotion_confidence": 0.3937463164329529, "duration_seconds": 2.048000000000002, "mos": 3.0687, "audio_variant": "cleaned", "original_transcript_raw": "Pronto le devolverán sus serpientes. ", "original_transcript": "Pronto le devolverán sus serpientes.", "retranscribed_transcript": "Pronto le devolverán sus serpientes.", "backend": "qwen", "emotion_analyzed_seconds": 2.048, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-119", "energy": { "value": 0.494140625, "bucket": "low" }, "audio_url": "audio/utterance-119.wav", "spectrogram_url": "spectrograms/utterance-119.png", "waveform": [ 0.03692, 0.02918, 0.02111, 0.00985, 0.04461, 0.24337, 0.4055, 0.48405, 0.28188, 0.56609, 0.49429, 0.48099, 0.44577, 0.36468, 0.30137, 0.25572, 0.19735, 0.13907, 0.09026, 0.0467, 0.00536, 0.00141, 0.0007, 0.00058, 0.00825, 0.04223, 0.22298, 0.32662, 0.36399, 0.31928, 0.25075, 0.19238, 0.18363, 0.1793, 0.1612, 0.18415, 0.28016, 0.32556, 0.3199, 0.26834, 0.20844, 0.14848, 0.10752, 0.10684, 0.14728, 0.25504, 0.30777, 0.3274, 0.2476, 0.09722, 0.07594, 0.10624, 0.18956, 0.26534, 0.30042, 0.30651, 0.22782, 0.21476, 0.22231, 0.15637, 0.04968, 0.02865, 0.02962, 0.09039, 0.23131, 0.35589, 0.36956, 0.3592, 0.15552, 0.17491, 0.2713, 0.3432, 0.31719, 0.3225, 0.2932, 0.2682, 0.23108, 0.17682, 0.11074, 0.05459, 0.04543, 0.04074, 0.04051, 0.03486, 0.02609, 0.01639, 0.0259, 0.12713, 0.13829, 0.12266, 0.09384, 0.0507, 0.03295, 0.02515, 0.03498, 0.03225, 0.03133, 0.04437, 0.03578, 0.01696, 0.16398, 0.2457, 0.2728, 0.29825, 0.28753, 0.31627, 0.09432, 0.03822, 0.05592, 0.07225, 0.07263, 0.04428, 0.01187, 0.00411, 0.00107, 0.00041, 0.00039, 0.00019, 0.00017, 0.01346, 0.0508, 0.10273, 0.12666, 0.15805, 0.18279, 0.23553, 0.26257, 0.25205, 0.23377, 0.22271, 0.24558, 0.24416, 0.20024, 0.10017, 0.10623, 0.11449, 0.10382, 0.06195, 0.0046, 0.00169, 0.00079, 0.0004, 0.00029, 0.00032, 0.029, 0.0285, 0.01397, 0.1558, 0.15997, 0.14349, 0.11319, 0.09444, 0.07912, 0.06921, 0.04037, 0.02091, 0.0112, 0.02265, 0.02355, 0.01911, 0.0175, 0.01976, 0.02721, 0.01788, 0.01228, 0.01271, 0.01251, 0.0143, 0.01093, 0.00857, 0.01524, 0.01104, 0.00561, 0.00064, 0.00036, 0.00144, 0.01239, 0.01522, 0.02652, 0.02451 ], "comparison": { "original": "Pronto le devolverán sus serpientes.", "retranscribed": "Pronto le devolverán sus serpientes.", "reference_tokens": [ "pronto", "le", "devolverán", "sus", "serpientes" ], "hypothesis_tokens": [ "pronto", "le", "devolverán", "sus", "serpientes" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "pronto", "hypothesis": "pronto", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "le", "hypothesis": "le", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "devolverán", "hypothesis": "devolverán", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "sus", "hypothesis": "sus", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "serpientes", "hypothesis": "serpientes", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.56609, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Sad", "emotion_confidence": 0.9501817226409912, "duration_seconds": 3.0720000000000027, "mos": 3.0042, "audio_variant": "original", "original_transcript_raw": "Cuando debió doler en el alma. ", "original_transcript": "Cuando debió doler en el alma.", "retranscribed_transcript": "Aun cuando debió doler en el alma.", "backend": "qwen", "emotion_analyzed_seconds": 3.072, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-120", "energy": { "value": 0.423828125, "bucket": "low" }, "audio_url": "audio/utterance-120.wav", "spectrogram_url": "spectrograms/utterance-120.png", "waveform": [ 0.04466, 0.06842, 0.21516, 0.23272, 0.28092, 0.22454, 0.24554, 0.22274, 0.17999, 0.28673, 0.25158, 0.35306, 0.37722, 0.43046, 0.41143, 0.21039, 0.43318, 0.52512, 0.21802, 0.16007, 0.22778, 0.16375, 0.16488, 0.17134, 0.17951, 0.08932, 0.07649, 0.06526, 0.06614, 0.07654, 0.06806, 0.04887, 0.0598, 0.05735, 0.04733, 0.04248, 0.04272, 0.05954, 0.05408, 0.05295, 0.06628, 0.06884, 0.05577, 0.03925, 0.03439, 0.03214, 0.02263, 0.03052, 0.02272, 0.0259, 0.02919, 0.03567, 0.03603, 0.03682, 0.02467, 0.02123, 0.02235, 0.02376, 0.02356, 0.03326, 0.0248, 0.02636, 0.02723, 0.02891, 0.02501, 0.02382, 0.02474, 0.0718, 0.08163, 0.0692, 0.05322, 0.04727, 0.05571, 0.04556, 0.05017, 0.04928, 0.05917, 0.07853, 0.28102, 0.35258, 0.18914, 0.16516, 0.14863, 0.11148, 0.13259, 0.11826, 0.05333, 0.26779, 0.24878, 0.32213, 0.32814, 0.20586, 0.07537, 0.05596, 0.05282, 0.25027, 0.3247, 0.28345, 0.18978, 0.09976, 0.06952, 0.07291, 0.07542, 0.05689, 0.09095, 0.11614, 0.15746, 0.24032, 0.26721, 0.16412, 0.12184, 0.1283, 0.08634, 0.06966, 0.06275, 0.06707, 0.05922, 0.20978, 0.25264, 0.22656, 0.13809, 0.12609, 0.11949, 0.13674, 0.11622, 0.13413, 0.19519, 0.26785, 0.30022, 0.30521, 0.32914, 0.21444, 0.34125, 0.41099, 0.44267, 0.34845, 0.17261, 0.08336, 0.21561, 0.14297, 0.13303, 0.09078, 0.03747, 0.0597, 0.05238, 0.04021, 0.05465, 0.14417, 0.21033, 0.25804, 0.23363, 0.19061, 0.11419, 0.0707, 0.08327, 0.15079, 0.20658, 0.09451, 0.17543, 0.13224, 0.07605, 0.1039, 0.10695, 0.04552, 0.07593, 0.16321, 0.10068, 0.06745, 0.06114, 0.06558, 0.06275, 0.08581, 0.03427, 0.1324, 0.11084, 0.05519, 0.03745, 0.03695, 0.03638, 0.02737 ], "comparison": { "original": "Cuando debió doler en el alma.", "retranscribed": "Aun cuando debió doler en el alma.", "reference_tokens": [ "cuando", "debió", "doler", "en", "el", "alma" ], "hypothesis_tokens": [ "aun", "cuando", "debió", "doler", "en", "el", "alma" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 6, "reference_words": 6, "hypothesis_words": 7, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "aun", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "cuando", "hypothesis": "cuando", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "debió", "hypothesis": "debió", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "doler", "hypothesis": "doler", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "en", "hypothesis": "en", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "el", "hypothesis": "el", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "alma", "hypothesis": "alma", "reference_index": 5, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.52512, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Sad", "emotion_confidence": 0.4694676101207733, "duration_seconds": 2.201999999999998, "mos": 3.1576, "audio_variant": "cleaned", "original_transcript_raw": "Cura sul sito sta limpio. ", "original_transcript": "Cura sul sito sta limpio.", "retranscribed_transcript": "tu corazón siento está limpio", "backend": "qwen", "emotion_analyzed_seconds": 2.202, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-121", "energy": { "value": 0.53515625, "bucket": "medium" }, "audio_url": "audio/utterance-121.wav", "spectrogram_url": "spectrograms/utterance-121.png", "waveform": [ 0.0153, 0.02365, 0.14625, 0.30621, 0.34215, 0.0818, 0.0083, 0.00263, 0.00439, 0.04726, 0.17306, 0.04449, 0.33106, 0.44706, 0.40607, 0.32409, 0.30353, 0.21283, 0.43865, 0.4131, 0.36775, 0.38413, 0.40473, 0.41252, 0.40159, 0.31487, 0.19691, 0.17408, 0.17097, 0.19709, 0.2336, 0.07025, 0.02769, 0.23235, 0.22558, 0.2381, 0.19577, 0.14362, 0.16714, 0.15846, 0.07461, 0.04148, 0.11824, 0.12216, 0.14609, 0.03207, 0.01964, 0.14147, 0.20265, 0.18942, 0.09116, 0.01701, 0.00324, 0.00421, 0.00144, 0.00137, 0.00183, 0.13343, 0.06192, 0.12648, 0.24891, 0.2601, 0.27446, 0.26434, 0.20754, 0.11592, 0.10754, 0.03281, 0.00778, 0.0029, 0.00268, 0.002, 0.00204, 0.14599, 0.08557, 0.22603, 0.19185, 0.29035, 0.2713, 0.3372, 0.30771, 0.30145, 0.31739, 0.30356, 0.27644, 0.26803, 0.24927, 0.2654, 0.32723, 0.33726, 0.31991, 0.29215, 0.26454, 0.23141, 0.21421, 0.22188, 0.23912, 0.23777, 0.19876, 0.20163, 0.20229, 0.19336, 0.19806, 0.1782, 0.08403, 0.02289, 0.00408, 0.00221, 0.00175, 0.13525, 0.03797, 0.17277, 0.19651, 0.18216, 0.21412, 0.1757, 0.17303, 0.17694, 0.16356, 0.13897, 0.12704, 0.11605, 0.11248, 0.07003, 0.0322, 0.01401, 0.0067, 0.00747, 0.01047, 0.01822, 0.00354, 0.00378, 0.00287, 0.00272, 0.00204, 0.00168, 0.00132, 0.00134, 0.00111, 0.00146, 0.00122, 0.00102, 0.00105, 0.00093, 0.00062, 0.00069, 0.00075, 0.00072, 0.0007, 0.00056, 0.00083, 0.00071, 0.00053, 0.00049, 0.00031, 0.00037, 0.00025, 0.00024, 0.00022, 0.00017, 9e-05, 0.00015, 0.00014, 8e-05, 7e-05, 7e-05, 7e-05, 8e-05, 8e-05, 8e-05, 0.00015, 0.00015, 0.00013, 0.00018, 0.00014, 0.00023, 0.0084, 0.01111, 0.02295, 0.03622 ], "comparison": { "original": "Cura sul sito sta limpio.", "retranscribed": "tu corazón siento está limpio", "reference_tokens": [ "cura", "sul", "sito", "sta", "limpio" ], "hypothesis_tokens": [ "tu", "corazón", "siento", "está", "limpio" ], "counts": { "substitutions": 4, "deletions": 0, "insertions": 0, "hits": 1, "reference_words": 5, "hypothesis_words": 5, "edits": 4 }, "wer": 0.8, "wer_percent": 80.0, "alignment": [ { "op": "substitute", "reference": "cura", "hypothesis": "tu", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "sul", "hypothesis": "corazón", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "sito", "hypothesis": "siento", "reference_index": 2, "hypothesis_index": 2 }, { "op": "substitute", "reference": "sta", "hypothesis": "está", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "limpio", "hypothesis": "limpio", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.44706, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Sad", "emotion_confidence": 0.4141908884048462, "duration_seconds": 3.5659999999999883, "mos": 2.9922, "audio_variant": "cleaned", "original_transcript_raw": "destrozado casi a punto de llorar porque", "original_transcript": "destrozado casi a punto de llorar porque", "retranscribed_transcript": "Destrozado, casi a punto de llorar porque", "backend": "qwen", "emotion_analyzed_seconds": 3.566, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-122", "energy": { "value": 0.546875, "bucket": "medium" }, "audio_url": "audio/utterance-122.wav", "spectrogram_url": "spectrograms/utterance-122.png", "waveform": [ 0.12764, 0.11313, 0.07339, 0.05085, 0.03409, 0.00874, 0.00103, 0.01546, 0.06957, 0.07402, 0.22841, 0.19306, 0.18696, 0.14075, 0.1202, 0.07297, 0.08473, 0.07955, 0.1142, 0.08868, 0.07146, 0.06054, 0.12239, 0.20685, 0.19649, 0.25901, 0.19268, 0.19517, 0.23857, 0.29403, 0.23739, 0.19836, 0.21842, 0.17345, 0.16978, 0.1168, 0.11988, 0.21956, 0.25143, 0.24747, 0.20301, 0.21975, 0.21016, 0.18993, 0.18002, 0.15472, 0.15939, 0.10765, 0.08104, 0.08198, 0.03797, 0.00097, 0.0003, 0.00024, 0.00019, 0.00013, 0.00011, 7e-05, 7e-05, 0.00085, 0.06553, 0.19341, 0.23662, 0.22426, 0.17124, 0.11399, 0.05842, 0.06967, 0.0824, 0.07041, 0.28677, 0.33447, 0.34763, 0.34842, 0.12749, 0.03541, 0.01051, 0.00123, 0.00013, 9e-05, 7e-05, 0.00064, 0.07037, 0.19234, 0.31257, 0.25625, 0.24379, 0.2138, 0.16039, 0.11709, 0.12223, 0.09516, 0.05938, 0.01275, 0.00067, 0.00022, 0.08241, 0.39244, 0.362, 0.28581, 0.23508, 0.07044, 0.0514, 0.05272, 0.27551, 0.26881, 0.23035, 0.22748, 0.19188, 0.16403, 0.07612, 0.04235, 0.07504, 0.14016, 0.24437, 0.28912, 0.27003, 0.30615, 0.30316, 0.11314, 0.15401, 0.28833, 0.34302, 0.34654, 0.351, 0.27534, 0.28742, 0.26936, 0.23743, 0.24812, 0.16382, 0.15823, 0.18467, 0.14312, 0.06115, 0.04286, 0.03627, 0.00729, 0.00479, 0.00762, 0.00401, 0.00025, 0.00016, 0.0001, 9e-05, 7e-05, 0.00096, 0.03309, 0.12958, 0.26117, 0.30043, 0.26178, 0.06414, 0.14525, 0.0758, 0.01931, 0.00498, 0.00038, 0.00302, 0.07362, 0.03534, 0.15865, 0.18974, 0.18746, 0.18524, 0.18721, 0.17367, 0.14774, 0.13635, 0.13101, 0.03934, 0.05996, 0.00737, 0.00037, 0.00012, 7e-05, 6e-05, 0.00295, 0.00794, 0.01632 ], "comparison": { "original": "destrozado casi a punto de llorar porque", "retranscribed": "Destrozado, casi a punto de llorar porque", "reference_tokens": [ "destrozado", "casi", "a", "punto", "de", "llorar", "porque" ], "hypothesis_tokens": [ "destrozado", "casi", "a", "punto", "de", "llorar", "porque" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 7, "reference_words": 7, "hypothesis_words": 7, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "destrozado", "hypothesis": "destrozado", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "casi", "hypothesis": "casi", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "a", "hypothesis": "a", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "punto", "hypothesis": "punto", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "de", "hypothesis": "de", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "llorar", "hypothesis": "llorar", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "porque", "hypothesis": "porque", "reference_index": 6, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.39244, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Sad", "emotion_confidence": 0.8733640909194946, "duration_seconds": 2.525999999999982, "mos": 3.5941, "audio_variant": "original", "original_transcript_raw": "Cercanas con la muerte. ", "original_transcript": "Cercanas con la muerte.", "retranscribed_transcript": "Cercanas con la muerte.", "backend": "qwen", "emotion_analyzed_seconds": 2.526, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-123", "energy": { "value": 0.5234375, "bucket": "medium" }, "audio_url": "audio/utterance-123.wav", "spectrogram_url": "spectrograms/utterance-123.png", "waveform": [ 0.00337, 0.00228, 0.00315, 0.00506, 0.01748, 0.03377, 0.0603, 0.06132, 0.06389, 0.13306, 0.19692, 0.222, 0.23703, 0.24717, 0.15163, 0.06979, 0.10784, 0.19426, 0.13936, 0.00619, 0.00438, 0.00262, 0.00263, 0.00499, 0.10713, 0.21503, 0.23318, 0.16195, 0.13451, 0.13719, 0.14033, 0.13562, 0.1463, 0.14836, 0.15037, 0.14207, 0.16699, 0.17266, 0.17158, 0.12335, 0.08163, 0.04573, 0.03022, 0.0423, 0.01898, 0.01972, 0.00945, 0.00678, 0.00382, 0.00243, 0.00239, 0.00294, 0.00302, 0.00349, 0.00298, 0.00252, 0.00226, 0.0024, 0.01428, 0.00722, 0.0022, 0.00296, 0.00205, 0.00224, 0.00215, 0.01813, 0.01315, 0.00233, 0.00247, 0.00252, 0.01006, 0.00329, 0.00281, 0.00236, 0.00216, 0.00204, 0.00241, 0.00293, 0.03317, 0.00238, 0.00249, 0.00205, 0.0026, 0.17628, 0.22535, 0.16527, 0.22158, 0.2202, 0.18926, 0.14443, 0.1422, 0.14303, 0.14783, 0.13858, 0.14521, 0.14127, 0.11649, 0.10071, 0.09767, 0.10489, 0.105, 0.11249, 0.12376, 0.12615, 0.12604, 0.10983, 0.10527, 0.07847, 0.05093, 0.03128, 0.03915, 0.00471, 0.00246, 0.00299, 0.00257, 0.00257, 0.00182, 0.00206, 0.00252, 0.00305, 0.00364, 0.00227, 0.00279, 0.12509, 0.18673, 0.179, 0.14844, 0.1429, 0.17492, 0.18175, 0.18609, 0.15096, 0.11158, 0.07917, 0.10111, 0.11759, 0.13356, 0.13606, 0.1366, 0.13219, 0.14409, 0.11203, 0.12324, 0.1317, 0.14878, 0.13145, 0.12542, 0.16425, 0.14197, 0.18538, 0.18988, 0.15142, 0.11616, 0.07614, 0.08353, 0.05867, 0.00512, 0.00324, 0.0031, 0.00304, 0.0028, 0.056, 0.0497, 0.07538, 0.10471, 0.12163, 0.09213, 0.1127, 0.06636, 0.07472, 0.06131, 0.04976, 0.0563, 0.031, 0.03742, 0.02946, 0.02328, 0.01686, 0.012, 0.00843 ], "comparison": { "original": "Cercanas con la muerte.", "retranscribed": "Cercanas con la muerte.", "reference_tokens": [ "cercanas", "con", "la", "muerte" ], "hypothesis_tokens": [ "cercanas", "con", "la", "muerte" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 4, "reference_words": 4, "hypothesis_words": 4, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "cercanas", "hypothesis": "cercanas", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "con", "hypothesis": "con", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "la", "hypothesis": "la", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "muerte", "hypothesis": "muerte", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.24717, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Sad", "emotion_confidence": 0.5105704665184021, "duration_seconds": 1.5700000000000074, "mos": 3.1079, "audio_variant": "original", "original_transcript_raw": "Siempre parecen mis sueños. ", "original_transcript": "Siempre parecen mis sueños.", "retranscribed_transcript": "siempre aparecen mis sueños", "backend": "qwen", "emotion_analyzed_seconds": 1.57, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-124", "energy": { "value": 0.58984375, "bucket": "high" }, "audio_url": "audio/utterance-124.wav", "spectrogram_url": "spectrograms/utterance-124.png", "waveform": [ 0.04714, 0.04195, 0.03889, 0.0408, 0.06503, 0.06366, 0.07404, 0.08057, 0.07326, 0.05569, 0.05179, 0.05391, 0.11737, 0.15747, 0.16925, 0.15037, 0.1395, 0.10677, 0.16338, 0.15314, 0.08254, 0.07621, 0.06038, 0.06304, 0.07854, 0.07668, 0.07443, 0.08299, 0.09332, 0.08406, 0.08894, 0.0883, 0.08718, 0.11399, 0.1125, 0.10691, 0.11438, 0.05864, 0.05247, 0.04715, 0.0431, 0.03525, 0.03727, 0.02906, 0.03472, 0.03409, 0.03535, 0.08412, 0.18892, 0.24234, 0.2826, 0.22436, 0.13285, 0.13698, 0.12782, 0.09541, 0.12337, 0.16136, 0.14468, 0.07756, 0.13658, 0.14548, 0.17089, 0.15203, 0.16611, 0.15816, 0.13803, 0.13699, 0.09776, 0.05182, 0.08022, 0.05148, 0.0414, 0.0335, 0.03876, 0.06251, 0.06437, 0.06911, 0.06937, 0.07061, 0.05802, 0.07007, 0.06486, 0.06849, 0.09658, 0.07978, 0.08171, 0.11805, 0.12453, 0.11452, 0.09959, 0.11036, 0.10741, 0.13156, 0.14454, 0.14406, 0.13257, 0.13713, 0.09854, 0.08569, 0.08245, 0.08307, 0.12312, 0.09502, 0.09005, 0.08686, 0.08875, 0.08342, 0.07424, 0.03653, 0.04065, 0.02988, 0.04145, 0.05085, 0.04375, 0.0462, 0.03644, 0.05686, 0.06547, 0.10374, 0.07389, 0.12235, 0.13422, 0.13709, 0.10644, 0.10278, 0.12419, 0.11553, 0.14831, 0.17146, 0.1441, 0.14395, 0.13412, 0.1206, 0.10299, 0.10351, 0.09993, 0.07512, 0.06113, 0.04613, 0.06705, 0.07836, 0.09979, 0.08544, 0.08839, 0.09667, 0.13587, 0.14349, 0.13432, 0.12641, 0.10661, 0.08397, 0.11353, 0.13982, 0.13958, 0.1438, 0.13399, 0.13615, 0.12433, 0.13139, 0.11871, 0.11135, 0.10196, 0.09501, 0.08115, 0.08157, 0.06429, 0.06856, 0.0625, 0.07407, 0.07459, 0.07958, 0.07455, 0.06453, 0.06546, 0.06485, 0.06888, 0.06078, 0.0584, 0.03638 ], "comparison": { "original": "Siempre parecen mis sueños.", "retranscribed": "siempre aparecen mis sueños", "reference_tokens": [ "siempre", "parecen", "mis", "sueños" ], "hypothesis_tokens": [ "siempre", "aparecen", "mis", "sueños" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 3, "reference_words": 4, "hypothesis_words": 4, "edits": 1 }, "wer": 0.25, "wer_percent": 25.0, "alignment": [ { "op": "equal", "reference": "siempre", "hypothesis": "siempre", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "parecen", "hypothesis": "aparecen", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "mis", "hypothesis": "mis", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "sueños", "hypothesis": "sueños", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.2826, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Sad", "emotion_confidence": 0.3625657856464386, "duration_seconds": 10.016999999999996, "mos": 3.3337, "audio_variant": "cleaned", "original_transcript_raw": "Me importa ser ladrón. No puede ser que no he encontrado todavía las palabras y esa noche no dije nada. ", "original_transcript": "Me importa ser ladrón. No puede ser que no he encontrado todavía las palabras y esa noche no dije nada.", "retranscribed_transcript": "No me importa ser ladrón no puede ser que no he encontrado todavía las palabras y esa noche no dije nada", "backend": "qwen", "emotion_analyzed_seconds": 10.017, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-125", "energy": { "value": 0.640625, "bucket": "high" }, "audio_url": "audio/utterance-125.wav", "spectrogram_url": "spectrograms/utterance-125.png", "waveform": [ 0.66615, 0.69735, 0.64082, 0.51491, 0.37005, 0.7037, 0.52329, 0.51606, 0.27237, 0.12406, 0.23581, 0.78096, 0.6784, 0.46849, 0.37993, 0.04122, 0.57931, 0.48584, 0.37868, 0.38995, 0.22693, 0.13156, 0.34635, 0.40023, 0.37988, 0.30782, 0.31896, 0.38776, 0.47428, 0.33029, 0.48152, 0.52152, 0.44956, 0.42432, 0.42173, 0.34938, 0.32349, 0.22115, 0.19468, 0.13564, 0.08503, 0.16644, 0.26869, 0.28677, 0.0843, 0.00034, 0.00086, 0.30721, 0.4437, 0.35597, 0.2964, 0.28236, 0.23745, 0.3343, 0.33289, 0.29081, 0.27829, 0.08642, 0.12501, 0.24498, 0.25439, 0.23808, 0.21597, 0.00092, 0.23158, 0.37964, 0.29475, 0.31662, 0.28481, 0.26922, 0.35678, 0.36704, 0.35811, 0.28427, 0.21361, 0.08643, 0.55617, 0.50224, 0.23249, 0.19674, 0.02562, 0.36825, 0.49147, 0.35997, 0.30848, 0.31374, 0.29073, 0.27854, 0.36619, 0.34589, 0.32656, 0.01785, 0.00049, 0.47427, 0.43337, 0.3346, 0.30886, 0.38738, 0.40094, 0.30205, 0.32113, 0.3153, 0.33059, 0.34645, 0.34012, 0.35678, 0.34671, 0.29934, 0.27244, 0.25324, 0.24193, 0.20877, 0.0898, 0.05633, 0.00062, 0.33268, 0.37206, 0.30512, 0.24763, 0.16865, 0.20778, 0.22508, 0.18078, 0.18122, 0.24063, 0.24616, 0.26882, 0.27812, 0.25959, 0.21231, 0.31739, 0.26248, 0.22248, 0.25287, 0.25221, 0.24471, 0.22783, 0.15578, 0.05895, 0.00938, 0.00602, 0.03741, 0.03506, 0.03344, 0.06672, 0.07469, 0.09652, 0.31113, 0.28183, 0.3275, 0.32233, 0.2705, 0.19508, 0.32654, 0.338, 0.28032, 0.21916, 0.39167, 0.38579, 0.31235, 0.26898, 0.24051, 0.27005, 0.24976, 0.22695, 0.26911, 0.29272, 0.28759, 0.22245, 0.334, 0.30514, 0.28273, 0.26823, 0.25466, 0.18048, 0.18839, 0.16723, 0.13046, 0.12769, 0.45354 ], "comparison": { "original": "Me importa ser ladrón. No puede ser que no he encontrado todavía las palabras y esa noche no dije nada.", "retranscribed": "No me importa ser ladrón no puede ser que no he encontrado todavía las palabras y esa noche no dije nada", "reference_tokens": [ "me", "importa", "ser", "ladrón", "no", "puede", "ser", "que", "no", "he", "encontrado", "todavía", "las", "palabras", "y", "esa", "noche", "no", "dije", "nada" ], "hypothesis_tokens": [ "no", "me", "importa", "ser", "ladrón", "no", "puede", "ser", "que", "no", "he", "encontrado", "todavía", "las", "palabras", "y", "esa", "noche", "no", "dije", "nada" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 20, "reference_words": 20, "hypothesis_words": 21, "edits": 1 }, "wer": 0.05, "wer_percent": 5.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "no", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "me", "hypothesis": "me", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "importa", "hypothesis": "importa", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "ser", "hypothesis": "ser", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "ladrón", "hypothesis": "ladrón", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "puede", "hypothesis": "puede", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "ser", "hypothesis": "ser", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 7, "hypothesis_index": 8 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 8, "hypothesis_index": 9 }, { "op": "equal", "reference": "he", "hypothesis": "he", "reference_index": 9, "hypothesis_index": 10 }, { "op": "equal", "reference": "encontrado", "hypothesis": "encontrado", "reference_index": 10, "hypothesis_index": 11 }, { "op": "equal", "reference": "todavía", "hypothesis": "todavía", "reference_index": 11, "hypothesis_index": 12 }, { "op": "equal", "reference": "las", "hypothesis": "las", "reference_index": 12, "hypothesis_index": 13 }, { "op": "equal", "reference": "palabras", "hypothesis": "palabras", "reference_index": 13, "hypothesis_index": 14 }, { "op": "equal", "reference": "y", "hypothesis": "y", "reference_index": 14, "hypothesis_index": 15 }, { "op": "equal", "reference": "esa", "hypothesis": "esa", "reference_index": 15, "hypothesis_index": 16 }, { "op": "equal", "reference": "noche", "hypothesis": "noche", "reference_index": 16, "hypothesis_index": 17 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 17, "hypothesis_index": 18 }, { "op": "equal", "reference": "dije", "hypothesis": "dije", "reference_index": 18, "hypothesis_index": 19 }, { "op": "equal", "reference": "nada", "hypothesis": "nada", "reference_index": 19, "hypothesis_index": 20 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.78096, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Sad", "emotion_confidence": 0.4167986810207367, "duration_seconds": 6.126000000000005, "mos": 3.0817, "audio_variant": "cleaned", "original_transcript_raw": "Que no vale uno nada si no tiene que no. ", "original_transcript": "Que no vale uno nada si no tiene que no.", "retranscribed_transcript": "Que no vale o no nada si no tiene quien nos va.", "backend": "qwen", "emotion_analyzed_seconds": 6.126, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-126", "energy": { "value": 0.8046875, "bucket": "high" }, "audio_url": "audio/utterance-126.wav", "spectrogram_url": "spectrograms/utterance-126.png", "waveform": [ 0.37959, 0.12541, 0.00479, 0.0035, 0.00462, 0.00794, 0.01191, 0.01139, 0.01097, 0.0119, 0.00449, 0.00096, 0.01567, 0.06794, 0.31108, 0.29667, 0.34608, 0.32934, 0.32826, 0.34005, 0.46304, 0.34835, 0.37469, 0.3924, 0.45799, 0.38719, 0.47867, 0.58472, 0.37846, 0.34156, 0.29914, 0.30624, 0.16451, 0.41525, 0.38682, 0.33659, 0.31428, 0.22153, 0.14094, 0.46719, 0.45192, 0.37567, 0.36742, 0.32143, 0.10906, 0.16057, 0.41019, 0.28587, 0.26999, 0.22975, 0.26446, 0.28713, 0.27719, 0.29213, 0.28563, 0.32598, 0.34282, 0.33022, 0.30996, 0.30446, 0.32177, 0.36618, 0.33779, 0.36321, 0.06785, 0.44706, 0.32324, 0.43364, 0.07554, 0.05026, 0.05854, 0.06082, 0.0509, 0.03651, 0.21994, 0.23615, 0.20175, 0.18297, 0.15193, 0.13524, 0.13208, 0.13412, 0.10647, 0.09865, 0.11136, 0.11828, 0.11619, 0.11264, 0.11842, 0.14598, 0.07254, 0.10778, 0.38014, 0.27511, 0.39157, 0.39682, 0.02371, 0.00512, 0.0511, 0.21885, 0.2304, 0.31482, 0.38954, 0.26948, 0.24728, 0.2423, 0.23362, 0.21005, 0.21771, 0.19936, 0.23841, 0.2288, 0.23262, 0.22404, 0.20288, 0.21194, 0.26818, 0.30706, 0.12361, 0.2443, 0.17462, 0.18642, 0.1034, 0.01197, 0.0447, 0.08167, 0.26227, 0.35575, 0.35719, 0.27638, 0.2862, 0.27182, 0.24674, 0.23191, 0.21108, 0.19075, 0.0537, 0.06648, 0.10437, 0.38896, 0.38314, 0.28598, 0.23532, 0.25005, 0.19488, 0.10217, 0.05046, 0.04244, 0.02076, 0.01601, 0.02493, 0.03105, 0.15594, 0.45451, 0.40626, 0.35776, 0.32241, 0.26405, 0.26587, 0.25547, 0.29637, 0.24537, 0.29667, 0.28308, 0.24598, 0.24847, 0.24461, 0.26338, 0.30008, 0.25801, 0.20493, 0.20178, 0.17721, 0.24221, 0.22283, 0.23196, 0.17073, 0.14111, 0.16598, 0.31887 ], "comparison": { "original": "Que no vale uno nada si no tiene que no.", "retranscribed": "Que no vale o no nada si no tiene quien nos va.", "reference_tokens": [ "que", "no", "vale", "uno", "nada", "si", "no", "tiene", "que", "no" ], "hypothesis_tokens": [ "que", "no", "vale", "o", "no", "nada", "si", "no", "tiene", "quien", "nos", "va" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 2, "hits": 7, "reference_words": 10, "hypothesis_words": 12, "edits": 5 }, "wer": 0.5, "wer_percent": 50.0, "alignment": [ { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "vale", "hypothesis": "vale", "reference_index": 2, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "o", "reference_index": null, "hypothesis_index": 3 }, { "op": "substitute", "reference": "uno", "hypothesis": "no", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "nada", "hypothesis": "nada", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "si", "hypothesis": "si", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "no", "hypothesis": "no", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "tiene", "hypothesis": "tiene", "reference_index": 7, "hypothesis_index": 8 }, { "op": "insert", "reference": null, "hypothesis": "quien", "reference_index": null, "hypothesis_index": 9 }, { "op": "substitute", "reference": "que", "hypothesis": "nos", "reference_index": 8, "hypothesis_index": 10 }, { "op": "substitute", "reference": "no", "hypothesis": "va", "reference_index": 9, "hypothesis_index": 11 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.58472, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Surprised", "emotion_confidence": 0.5510022640228271, "duration_seconds": 0.46100000000001273, "mos": 3.5278, "audio_variant": "cleaned", "original_transcript_raw": "Еста", "original_transcript": "Еста", "retranscribed_transcript": "¿Dónde está", "backend": "qwen", "emotion_analyzed_seconds": 0.461, "emotion_crop_policy": "center_crop_20s", "duration_supplement": true, "id": "utterance-127", "energy": { "value": 0.50390625, "bucket": "low" }, "audio_url": "audio/utterance-127.wav", "spectrogram_url": "spectrograms/utterance-127.png", "waveform": [ 0.04159, 0.04867, 0.03367, 0.0517, 0.07224, 0.03982, 0.01818, 0.06, 0.08304, 0.05348, 0.02536, 0.04, 0.08286, 0.05902, 0.0244, 0.05761, 0.09536, 0.05004, 0.03032, 0.06655, 0.11045, 0.04006, 0.05934, 0.05165, 0.12097, 0.05665, 0.04565, 0.06347, 0.12724, 0.06024, 0.05251, 0.07009, 0.12942, 0.06794, 0.05369, 0.06225, 0.13046, 0.05308, 0.05606, 0.05635, 0.09119, 0.1016, 0.05176, 0.05224, 0.08057, 0.04959, 0.05174, 0.04854, 0.05813, 0.04651, 0.06092, 0.07098, 0.07022, 0.06062, 0.06494, 0.06718, 0.07126, 0.05007, 0.07277, 0.05687, 0.05584, 0.05216, 0.06834, 0.05067, 0.05943, 0.05187, 0.04179, 0.04355, 0.0242, 0.01765, 0.01302, 0.00947, 0.00822, 0.00353, 0.00179, 0.0014, 0.00101, 0.00068, 0.00093, 0.00069, 0.00078, 0.00074, 0.00117, 0.00104, 0.00248, 0.00397, 0.0081, 0.0061, 0.01133, 0.01857, 0.0157, 0.02284, 0.0323, 0.04375, 0.02462, 0.02773, 0.04589, 0.05362, 0.0266, 0.1908, 0.12691, 0.1108, 0.23836, 0.25435, 0.13111, 0.11545, 0.31196, 0.08947, 0.07692, 0.29573, 0.11377, 0.07214, 0.26086, 0.11271, 0.05333, 0.24741, 0.11454, 0.12377, 0.19948, 0.10313, 0.19998, 0.08104, 0.10241, 0.15919, 0.12039, 0.16174, 0.15777, 0.11865, 0.17971, 0.10588, 0.16421, 0.09756, 0.09492, 0.19069, 0.10167, 0.1521, 0.11117, 0.19976, 0.10524, 0.16492, 0.13785, 0.18486, 0.14149, 0.19661, 0.16749, 0.21764, 0.16482, 0.21663, 0.14887, 0.22472, 0.1099, 0.2259, 0.11978, 0.25173, 0.20763, 0.1382, 0.15725, 0.13076, 0.123, 0.11683, 0.11849, 0.11037, 0.10425, 0.09344, 0.08511, 0.07992, 0.07309, 0.06849, 0.0607, 0.05197, 0.04581, 0.03884, 0.03109, 0.03952, 0.03369, 0.0331, 0.03029, 0.02137, 0.02114, 0.0361 ], "comparison": { "original": "Еста", "retranscribed": "¿Dónde está", "reference_tokens": [ "еста" ], "hypothesis_tokens": [ "dónde", "está" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 1, "hits": 0, "reference_words": 1, "hypothesis_words": 2, "edits": 2 }, "wer": 2.0, "wer_percent": 200.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "dónde", "reference_index": null, "hypothesis_index": 0 }, { "op": "substitute", "reference": "еста", "hypothesis": "está", "reference_index": 0, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.31196, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Surprised", "emotion_confidence": 0.4313758313655853, "duration_seconds": 3.0720000000000027, "mos": 2.9497, "audio_variant": "cleaned", "original_transcript_raw": "Este mundo podría ser tu", "original_transcript": "Este mundo podría ser tu", "retranscribed_transcript": "Este mundo podría ser todo.", "backend": "qwen", "emotion_analyzed_seconds": 3.072, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-128", "energy": { "value": 0.478515625, "bucket": "low" }, "audio_url": "audio/utterance-128.wav", "spectrogram_url": "spectrograms/utterance-128.png", "waveform": [ 0.06218, 0.1707, 0.30184, 0.32872, 0.33226, 0.41003, 0.3889, 0.34024, 0.18768, 0.12692, 0.1069, 0.08638, 0.07852, 0.08423, 0.03117, 0.00671, 0.0011, 0.0007, 0.00059, 0.00071, 0.00084, 0.13742, 0.4087, 0.70907, 0.62323, 0.49287, 0.20461, 0.05919, 0.03296, 0.02895, 0.02821, 0.01148, 0.00547, 0.00454, 0.00478, 0.00392, 0.00244, 0.00214, 0.00293, 0.00426, 0.00585, 0.00879, 0.02517, 0.57242, 0.68867, 0.71629, 0.70389, 0.65033, 0.60038, 0.58214, 0.58045, 0.45174, 0.36363, 0.29768, 0.42048, 0.53195, 0.54045, 0.55984, 0.56845, 0.54448, 0.51607, 0.4415, 0.33065, 0.25348, 0.13281, 0.05801, 0.08358, 0.09308, 0.11392, 0.09337, 0.08997, 0.09193, 0.05574, 0.04929, 0.04833, 0.03056, 0.01675, 0.00796, 0.00263, 0.00185, 0.00125, 0.00121, 0.00122, 0.00107, 0.00106, 0.00067, 0.00079, 0.00086, 0.00126, 0.00105, 0.00115, 0.00092, 0.00078, 0.00063, 0.0009, 0.00092, 0.00064, 0.00075, 0.00091, 0.00084, 0.00107, 0.00086, 0.00076, 0.00105, 0.00087, 0.00082, 0.00103, 0.00077, 0.16711, 0.28742, 0.73716, 0.78941, 0.71821, 0.4439, 0.31892, 0.0633, 0.03346, 0.03819, 0.57792, 0.72227, 0.70841, 0.16323, 0.48609, 0.51943, 0.44946, 0.36405, 0.36094, 0.34316, 0.33833, 0.35215, 0.35341, 0.28456, 0.23254, 0.07023, 0.04519, 0.0574, 0.06533, 0.08715, 0.08395, 0.06472, 0.05152, 0.18275, 0.26118, 0.26496, 0.26076, 0.2716, 0.27978, 0.2869, 0.2957, 0.28406, 0.2826, 0.2689, 0.27928, 0.26468, 0.28158, 0.03475, 0.05879, 0.03214, 0.02213, 0.00651, 0.00455, 0.00141, 0.00115, 0.00116, 0.0008, 0.00087, 0.0008, 0.09518, 0.44754, 0.51653, 0.51075, 0.42737, 0.33943, 0.3999, 0.58464, 0.64297, 0.55588, 0.3904, 0.13147, 0.02048 ], "comparison": { "original": "Este mundo podría ser tu", "retranscribed": "Este mundo podría ser todo.", "reference_tokens": [ "este", "mundo", "podría", "ser", "tu" ], "hypothesis_tokens": [ "este", "mundo", "podría", "ser", "todo" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 4, "reference_words": 5, "hypothesis_words": 5, "edits": 1 }, "wer": 0.2, "wer_percent": 20.0, "alignment": [ { "op": "equal", "reference": "este", "hypothesis": "este", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "mundo", "hypothesis": "mundo", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "podría", "hypothesis": "podría", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "ser", "hypothesis": "ser", "reference_index": 3, "hypothesis_index": 3 }, { "op": "substitute", "reference": "tu", "hypothesis": "todo", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.78941, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Surprised", "emotion_confidence": 0.5753903985023499, "duration_seconds": 2.0649999999999977, "mos": 3.687, "audio_variant": "cleaned", "original_transcript_raw": "Ah, oye, estás bien. Sí. ", "original_transcript": "Ah, oye, estás bien. Sí.", "retranscribed_transcript": "Oye, estás bien.", "backend": "qwen", "emotion_analyzed_seconds": 2.065, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-129", "energy": { "value": 0.5, "bucket": "low" }, "audio_url": "audio/utterance-129.wav", "spectrogram_url": "spectrograms/utterance-129.png", "waveform": [ 0.11006, 0.13425, 0.06773, 0.12518, 0.2064, 0.22033, 0.19472, 0.20869, 0.20436, 0.23214, 0.22751, 0.22147, 0.21717, 0.25034, 0.23321, 0.26279, 0.25386, 0.21078, 0.23841, 0.27117, 0.26075, 0.2058, 0.20353, 0.12726, 0.04005, 0.0245, 0.02256, 0.01194, 0.00866, 0.0043, 0.00298, 0.00407, 0.01803, 0.13143, 0.2101, 0.19867, 0.20011, 0.2535, 0.26901, 0.23337, 0.25513, 0.22354, 0.22256, 0.16979, 0.06222, 0.05895, 0.05832, 0.08207, 0.12193, 0.21936, 0.27382, 0.30643, 0.32328, 0.28953, 0.29364, 0.29384, 0.2791, 0.23831, 0.25557, 0.22846, 0.20409, 0.16542, 0.06837, 0.01522, 0.00621, 0.00186, 0.00067, 0.00031, 0.00026, 0.00026, 0.00022, 0.00019, 0.00017, 0.00013, 0.00012, 0.0001, 0.0001, 0.0001, 0.00011, 0.00014, 0.00019, 0.00053, 0.00075, 0.00118, 0.00185, 0.00717, 0.0317, 0.05179, 0.04917, 0.04282, 0.03775, 0.03658, 0.03293, 0.01838, 0.00453, 0.00118, 0.00038, 0.00022, 0.00017, 0.00015, 0.00195, 0.04452, 0.04906, 0.09792, 0.11795, 0.13986, 0.18479, 0.13349, 0.07984, 0.05099, 0.04235, 0.03622, 0.03627, 0.03572, 0.01639, 0.00551, 0.00191, 0.00438, 0.01357, 0.05225, 0.05077, 0.0717, 0.08586, 0.07863, 0.08726, 0.1221, 0.10483, 0.13785, 0.13229, 0.13224, 0.08771, 0.04823, 0.04188, 0.06718, 0.06166, 0.0696, 0.07202, 0.06359, 0.0453, 0.04213, 0.02465, 0.00731, 0.00224, 0.001, 0.00032, 0.00033, 0.00025, 0.00018, 0.00017, 0.00015, 0.00014, 0.00026, 0.00532, 0.01677, 0.02038, 0.01784, 0.02268, 0.01751, 0.01094, 0.0138, 0.01323, 0.01076, 0.03529, 0.16652, 0.23328, 0.22237, 0.20353, 0.20283, 0.1742, 0.16115, 0.13868, 0.11902, 0.0778, 0.05577, 0.0348, 0.02839, 0.02722, 0.03716, 0.06111, 0.10246 ], "comparison": { "original": "Ah, oye, estás bien. Sí.", "retranscribed": "Oye, estás bien.", "reference_tokens": [ "ah", "oye", "estás", "bien", "sí" ], "hypothesis_tokens": [ "oye", "estás", "bien" ], "counts": { "substitutions": 0, "deletions": 2, "insertions": 0, "hits": 3, "reference_words": 5, "hypothesis_words": 3, "edits": 2 }, "wer": 0.4, "wer_percent": 40.0, "alignment": [ { "op": "delete", "reference": "ah", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "equal", "reference": "oye", "hypothesis": "oye", "reference_index": 1, "hypothesis_index": 0 }, { "op": "equal", "reference": "estás", "hypothesis": "estás", "reference_index": 2, "hypothesis_index": 1 }, { "op": "equal", "reference": "bien", "hypothesis": "bien", "reference_index": 3, "hypothesis_index": 2 }, { "op": "delete", "reference": "sí", "hypothesis": null, "reference_index": 4, "hypothesis_index": null } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.32328, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Surprised", "emotion_confidence": 0.7354999780654907, "duration_seconds": 0.9900000000000091, "mos": 2.9681, "audio_variant": "cleaned", "original_transcript_raw": "ナ ジ ョ デ ナ ル ご", "original_transcript": "ナ ジ ョ デ ナ ル ご", "retranscribed_transcript": "Ayuden algo.", "backend": "qwen", "emotion_analyzed_seconds": 0.99, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-130", "energy": { "value": 0.5703125, "bucket": "medium" }, "audio_url": "audio/utterance-130.wav", "spectrogram_url": "spectrograms/utterance-130.png", "waveform": [ 0.01139, 0.01869, 0.06068, 0.1424, 0.15488, 0.22065, 0.19486, 0.22906, 0.22268, 0.18543, 0.21736, 0.2117, 0.26549, 0.22384, 0.25366, 0.28558, 0.29599, 0.27147, 0.23378, 0.18078, 0.14424, 0.14797, 0.09771, 0.08242, 0.06879, 0.05517, 0.05768, 0.05589, 0.07136, 0.06836, 0.06106, 0.07081, 0.09039, 0.11636, 0.17698, 0.19387, 0.20014, 0.19335, 0.19638, 0.17856, 0.17482, 0.15998, 0.14977, 0.14515, 0.10989, 0.06404, 0.04386, 0.02863, 0.02366, 0.02658, 0.03764, 0.06261, 0.12498, 0.16094, 0.18989, 0.25351, 0.23736, 0.23686, 0.23082, 0.19555, 0.18662, 0.19639, 0.23254, 0.2152, 0.19469, 0.20641, 0.19517, 0.1709, 0.17704, 0.15079, 0.1581, 0.13532, 0.1306, 0.11395, 0.13781, 0.14565, 0.14627, 0.14904, 0.15263, 0.14981, 0.14565, 0.15285, 0.15271, 0.15708, 0.18168, 0.20573, 0.21864, 0.21385, 0.23609, 0.23075, 0.25279, 0.27343, 0.26794, 0.25401, 0.28743, 0.27725, 0.26686, 0.25013, 0.23506, 0.20372, 0.21623, 0.18152, 0.19546, 0.17587, 0.17387, 0.16911, 0.16175, 0.16087, 0.15349, 0.15374, 0.15055, 0.14133, 0.13527, 0.12956, 0.10094, 0.07308, 0.04609, 0.03194, 0.01838, 0.01883, 0.01628, 0.02363, 0.03095, 0.02177, 0.046, 0.03501, 0.03569, 0.09651, 0.12819, 0.16514, 0.16452, 0.21285, 0.24535, 0.23269, 0.21033, 0.18583, 0.19063, 0.17504, 0.19395, 0.15265, 0.12283, 0.09401, 0.08946, 0.06901, 0.06024, 0.0623, 0.0422, 0.0417, 0.03989, 0.03339, 0.01651, 0.03054, 0.03316, 0.02301, 0.02021, 0.02289, 0.01906, 0.01509, 0.01484, 0.01755, 0.01204, 0.00455, 0.00265, 0.00295, 0.00105, 0.00095, 0.00029, 0.00036, 0.00017, 0.00013, 0.0001, 0.00046, 0.00154, 0.00329, 0.00287, 0.00387, 0.00803, 0.00494, 0.00845, 0.00989 ], "comparison": { "original": "ナ ジ ョ デ ナ ル ご", "retranscribed": "Ayuden algo.", "reference_tokens": [ "ナ", "ジ", "ョ", "デ", "ナ", "ル", "ご" ], "hypothesis_tokens": [ "ayuden", "algo" ], "counts": { "substitutions": 2, "deletions": 5, "insertions": 0, "hits": 0, "reference_words": 7, "hypothesis_words": 2, "edits": 7 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "delete", "reference": "ナ", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "delete", "reference": "ジ", "hypothesis": null, "reference_index": 1, "hypothesis_index": null }, { "op": "delete", "reference": "ョ", "hypothesis": null, "reference_index": 2, "hypothesis_index": null }, { "op": "delete", "reference": "デ", "hypothesis": null, "reference_index": 3, "hypothesis_index": null }, { "op": "delete", "reference": "ナ", "hypothesis": null, "reference_index": 4, "hypothesis_index": null }, { "op": "substitute", "reference": "ル", "hypothesis": "ayuden", "reference_index": 5, "hypothesis_index": 0 }, { "op": "substitute", "reference": "ご", "hypothesis": "algo", "reference_index": 6, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.29599, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Surprised", "emotion_confidence": 0.533772885799408, "duration_seconds": 0.5630000000000024, "mos": 3.0015, "audio_variant": "original", "original_transcript_raw": "Oh yeah. ", "original_transcript": "Oh yeah.", "retranscribed_transcript": "Oye.", "backend": "qwen", "emotion_analyzed_seconds": 0.563, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-131", "energy": { "value": 0.546875, "bucket": "medium" }, "audio_url": "audio/utterance-131.wav", "spectrogram_url": "spectrograms/utterance-131.png", "waveform": [ 0.03335, 0.03872, 0.03953, 0.02586, 0.0341, 0.03257, 0.02501, 0.03916, 0.06582, 0.05179, 0.14845, 0.06414, 0.0929, 0.1803, 0.11975, 0.1457, 0.15433, 0.11415, 0.18304, 0.11426, 0.17956, 0.13977, 0.24062, 0.2192, 0.13025, 0.20245, 0.18659, 0.23979, 0.2252, 0.15401, 0.282, 0.16642, 0.22931, 0.13206, 0.34356, 0.18008, 0.28886, 0.2646, 0.11992, 0.40136, 0.16541, 0.3018, 0.24938, 0.20958, 0.20908, 0.17446, 0.21583, 0.19099, 0.10721, 0.19286, 0.12597, 0.11844, 0.1938, 0.0793, 0.1774, 0.09257, 0.14787, 0.15293, 0.14103, 0.20731, 0.14511, 0.20794, 0.26307, 0.10689, 0.30943, 0.14552, 0.31334, 0.39988, 0.17069, 0.36503, 0.21871, 0.28823, 0.20192, 0.10392, 0.20446, 0.13738, 0.14761, 0.17842, 0.15405, 0.13716, 0.19259, 0.15456, 0.19302, 0.18604, 0.15921, 0.15079, 0.08346, 0.09417, 0.14301, 0.10047, 0.07329, 0.08806, 0.08007, 0.09079, 0.20146, 0.13929, 0.05003, 0.09373, 0.09201, 0.07709, 0.06331, 0.10801, 0.09347, 0.03926, 0.05151, 0.07213, 0.06213, 0.06244, 0.03653, 0.04026, 0.08243, 0.08383, 0.0395, 0.08345, 0.07883, 0.07528, 0.05061, 0.04495, 0.06121, 0.05138, 0.04775, 0.04831, 0.04717, 0.03709, 0.0433, 0.04664, 0.06406, 0.05318, 0.03063, 0.054, 0.04582, 0.04841, 0.04665, 0.03475, 0.03146, 0.04263, 0.02475, 0.03428, 0.04931, 0.04033, 0.02543, 0.03803, 0.03688, 0.0465, 0.03806, 0.02454, 0.01731, 0.02317, 0.02072, 0.02379, 0.04152, 0.04479, 0.02632, 0.02182, 0.04331, 0.03528, 0.03002, 0.03947, 0.03961, 0.05409, 0.02232, 0.01953, 0.06386, 0.06421, 0.02902, 0.035, 0.03293, 0.01907, 0.02017, 0.01744, 0.04232, 0.04361, 0.05115, 0.03284, 0.05689, 0.059, 0.02582, 0.02975, 0.02541, 0.01443 ], "comparison": { "original": "Oh yeah.", "retranscribed": "Oye.", "reference_tokens": [ "oh", "yeah" ], "hypothesis_tokens": [ "oye" ], "counts": { "substitutions": 1, "deletions": 1, "insertions": 0, "hits": 0, "reference_words": 2, "hypothesis_words": 1, "edits": 2 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "delete", "reference": "oh", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "substitute", "reference": "yeah", "hypothesis": "oye", "reference_index": 1, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.40136, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Surprised", "emotion_confidence": 0.42281201481819153, "duration_seconds": 2.4740000000000038, "mos": 3.5503, "audio_variant": "cleaned", "original_transcript_raw": "Lo que le pasará si nos deja en paz. ", "original_transcript": "Lo que le pasará si nos deja en paz.", "retranscribed_transcript": "Lo que le pasaría si nos dejan paz.", "backend": "qwen", "emotion_analyzed_seconds": 2.474, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-132", "energy": { "value": 0.56640625, "bucket": "medium" }, "audio_url": "audio/utterance-132.wav", "spectrogram_url": "spectrograms/utterance-132.png", "waveform": [ 0.00738, 0.00505, 0.00436, 0.02037, 0.27778, 0.43544, 0.15925, 0.08796, 0.01252, 0.00485, 0.00151, 0.00143, 0.00129, 0.00058, 0.00064, 0.00179, 0.22439, 0.13257, 0.14349, 0.33864, 0.40434, 0.35786, 0.34267, 0.33019, 0.3628, 0.38786, 0.32681, 0.33285, 0.38928, 0.3901, 0.36044, 0.32392, 0.29154, 0.2262, 0.15315, 0.10435, 0.09314, 0.10535, 0.09441, 0.10015, 0.08777, 0.0926, 0.04286, 0.02223, 0.02425, 0.02428, 0.01991, 0.0265, 0.02684, 0.02163, 0.01452, 0.00626, 0.00133, 0.00052, 0.00085, 0.00062, 0.00039, 0.0002, 0.00051, 0.00034, 0.00034, 0.00037, 0.00032, 0.00024, 0.00011, 0.00018, 0.00014, 0.00059, 0.00173, 0.00627, 0.15236, 0.19446, 0.49801, 0.30961, 0.2979, 0.18068, 0.05545, 0.02998, 0.00716, 0.00305, 0.11276, 0.40451, 0.59874, 0.52442, 0.30106, 0.27593, 0.40053, 0.47105, 0.55406, 0.45023, 0.12711, 0.05845, 0.01487, 0.02356, 0.2309, 0.55331, 0.45303, 0.47381, 0.3549, 0.12422, 0.10213, 0.10504, 0.12753, 0.07113, 0.12494, 0.39454, 0.44154, 0.47404, 0.44848, 0.44302, 0.13731, 0.24205, 0.35871, 0.45771, 0.5299, 0.4946, 0.49402, 0.44152, 0.48544, 0.49101, 0.47663, 0.34243, 0.10808, 0.08039, 0.06998, 0.04895, 0.07112, 0.03597, 0.03326, 0.36534, 0.35928, 0.3627, 0.32063, 0.36922, 0.29668, 0.25139, 0.20564, 0.14885, 0.09588, 0.04993, 0.06713, 0.18145, 0.39377, 0.40759, 0.41207, 0.39821, 0.24035, 0.10469, 0.05813, 0.03198, 0.02535, 0.26511, 0.39118, 0.3341, 0.30205, 0.25509, 0.19754, 0.18098, 0.13256, 0.04626, 0.01725, 0.02992, 0.29685, 0.5118, 0.36166, 0.36113, 0.35223, 0.3628, 0.2735, 0.25774, 0.07651, 0.05026, 0.06646, 0.06332, 0.08367, 0.08995, 0.11428, 0.06479, 0.05906, 0.05114 ], "comparison": { "original": "Lo que le pasará si nos deja en paz.", "retranscribed": "Lo que le pasaría si nos dejan paz.", "reference_tokens": [ "lo", "que", "le", "pasará", "si", "nos", "deja", "en", "paz" ], "hypothesis_tokens": [ "lo", "que", "le", "pasaría", "si", "nos", "dejan", "paz" ], "counts": { "substitutions": 2, "deletions": 1, "insertions": 0, "hits": 6, "reference_words": 9, "hypothesis_words": 8, "edits": 3 }, "wer": 0.3333333333333333, "wer_percent": 33.33333333333333, "alignment": [ { "op": "equal", "reference": "lo", "hypothesis": "lo", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "le", "hypothesis": "le", "reference_index": 2, "hypothesis_index": 2 }, { "op": "substitute", "reference": "pasará", "hypothesis": "pasaría", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "si", "hypothesis": "si", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "nos", "hypothesis": "nos", "reference_index": 5, "hypothesis_index": 5 }, { "op": "delete", "reference": "deja", "hypothesis": null, "reference_index": 6, "hypothesis_index": null }, { "op": "substitute", "reference": "en", "hypothesis": "dejan", "reference_index": 7, "hypothesis_index": 6 }, { "op": "equal", "reference": "paz", "hypothesis": "paz", "reference_index": 8, "hypothesis_index": 7 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.59874, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Surprised", "emotion_confidence": 0.27302876114845276, "duration_seconds": 2.5939999999999994, "mos": 2.9438, "audio_variant": "cleaned", "original_transcript_raw": "Dio a quien mi attrappe. ", "original_transcript": "Dio a quien mi attrappe.", "retranscribed_transcript": "Dio que me atrape.", "backend": "qwen", "emotion_analyzed_seconds": 2.594, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-133", "energy": { "value": 0.8125, "bucket": "high" }, "audio_url": "audio/utterance-133.wav", "spectrogram_url": "spectrograms/utterance-133.png", "waveform": [ 0.08282, 0.0477, 0.02483, 0.03738, 0.04599, 0.04787, 0.05959, 0.13929, 0.13039, 0.12701, 0.26021, 0.17883, 0.26962, 0.42048, 0.33983, 0.32329, 0.23118, 0.24881, 0.11832, 0.04468, 0.01711, 0.00625, 0.00186, 0.00154, 0.00149, 0.00139, 0.00161, 0.00216, 0.00257, 0.00262, 0.00214, 0.00392, 0.00234, 0.00229, 0.0015, 0.00131, 0.00098, 0.00087, 0.00083, 0.00209, 0.00699, 0.00734, 0.01075, 0.01769, 0.02329, 0.07705, 0.12537, 0.14055, 0.22034, 0.23929, 0.25855, 0.36994, 0.36979, 0.23565, 0.25557, 0.45514, 0.32633, 0.27203, 0.19267, 0.24398, 0.33332, 0.47759, 0.47896, 0.40633, 0.37683, 0.3189, 0.10026, 0.06416, 0.01725, 0.00399, 0.00226, 0.00051, 0.00045, 0.06351, 0.09314, 0.15855, 0.21709, 0.21191, 0.23177, 0.291, 0.41512, 0.41112, 0.19277, 0.1456, 0.14239, 0.14447, 0.14715, 0.15354, 0.15892, 0.1703, 0.26108, 0.26816, 0.31485, 0.34544, 0.18497, 0.41652, 0.34442, 0.24414, 0.2714, 0.23613, 0.24918, 0.25889, 0.1095, 0.03605, 0.04024, 0.03078, 0.02493, 0.01473, 0.00499, 0.04272, 0.08801, 0.21524, 0.15435, 0.09194, 0.20735, 0.20794, 0.16984, 0.20947, 0.16448, 0.1063, 0.13236, 0.19522, 0.2394, 0.24824, 0.22329, 0.35383, 0.52552, 0.26063, 0.07808, 0.05569, 0.03163, 0.01471, 0.00577, 0.00191, 0.07049, 0.06391, 0.15572, 0.19068, 0.25408, 0.26097, 0.25525, 0.24726, 0.25239, 0.2448, 0.24906, 0.25321, 0.24716, 0.22838, 0.19829, 0.2046, 0.22117, 0.21291, 0.18442, 0.15632, 0.15179, 0.12558, 0.09578, 0.05107, 0.01095, 0.00363, 0.00115, 0.00073, 0.01078, 0.06645, 0.10497, 0.09835, 0.11465, 0.06296, 0.02171, 0.00936, 0.00308, 0.00117, 0.00033, 0.0002, 0.00015, 0.00022, 0.00027, 0.03332, 0.04227, 0.04924 ], "comparison": { "original": "Dio a quien mi attrappe.", "retranscribed": "Dio que me atrape.", "reference_tokens": [ "dio", "a", "quien", "mi", "attrappe" ], "hypothesis_tokens": [ "dio", "que", "me", "atrape" ], "counts": { "substitutions": 3, "deletions": 1, "insertions": 0, "hits": 1, "reference_words": 5, "hypothesis_words": 4, "edits": 4 }, "wer": 0.8, "wer_percent": 80.0, "alignment": [ { "op": "equal", "reference": "dio", "hypothesis": "dio", "reference_index": 0, "hypothesis_index": 0 }, { "op": "delete", "reference": "a", "hypothesis": null, "reference_index": 1, "hypothesis_index": null }, { "op": "substitute", "reference": "quien", "hypothesis": "que", "reference_index": 2, "hypothesis_index": 1 }, { "op": "substitute", "reference": "mi", "hypothesis": "me", "reference_index": 3, "hypothesis_index": 2 }, { "op": "substitute", "reference": "attrappe", "hypothesis": "atrape", "reference_index": 4, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.52552, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Surprised", "emotion_confidence": 0.6282361745834351, "duration_seconds": 2.8160000000000025, "mos": 2.8638, "audio_variant": "cleaned", "original_transcript_raw": "Se supone que es el gerente. ", "original_transcript": "Se supone que es el gerente.", "retranscribed_transcript": "Y se supone que es el gerente. Hola.", "backend": "qwen", "emotion_analyzed_seconds": 2.816, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-134", "energy": { "value": 0.58984375, "bucket": "high" }, "audio_url": "audio/utterance-134.wav", "spectrogram_url": "spectrograms/utterance-134.png", "waveform": [ 0.01858, 0.15927, 0.34219, 0.25675, 0.14976, 0.09987, 0.09068, 0.07002, 0.04294, 0.03097, 0.02919, 0.02261, 0.01034, 0.38881, 0.26617, 0.32191, 0.23248, 0.13155, 0.06608, 0.0487, 0.06512, 0.04942, 0.15995, 0.31073, 0.29934, 0.16707, 0.08935, 0.07705, 0.08976, 0.09028, 0.15996, 0.1094, 0.06096, 0.01704, 0.01136, 0.06927, 0.26807, 0.34253, 0.37741, 0.29268, 0.19701, 0.1817, 0.15938, 0.15158, 0.188, 0.19453, 0.16936, 0.08634, 0.0067, 0.09599, 0.13172, 0.27827, 0.38438, 0.28615, 0.17639, 0.07494, 0.05787, 0.06543, 0.15804, 0.26845, 0.20803, 0.21416, 0.28206, 0.2233, 0.14923, 0.04634, 0.03677, 0.07939, 0.21771, 0.36611, 0.36518, 0.2592, 0.13406, 0.17071, 0.18211, 0.26489, 0.27216, 0.23871, 0.17696, 0.19577, 0.13752, 0.06903, 0.04381, 0.01925, 0.04815, 0.19647, 0.20365, 0.21256, 0.25898, 0.21388, 0.18667, 0.17689, 0.16334, 0.08157, 0.07151, 0.043, 0.02161, 0.00587, 0.00317, 0.00206, 0.00206, 0.00197, 0.00085, 0.00044, 0.01607, 0.03585, 0.0594, 0.06901, 0.07048, 0.20601, 0.38131, 0.28274, 0.29893, 0.23434, 0.18194, 0.11521, 0.07272, 0.02845, 0.02363, 0.00924, 0.00559, 0.00224, 0.00168, 0.0018, 0.00346, 0.00691, 0.01099, 0.11981, 0.11983, 0.12998, 0.12052, 0.07806, 0.08762, 0.18849, 0.13491, 0.1104, 0.11683, 0.12345, 0.13074, 0.13218, 0.14746, 0.15527, 0.15404, 0.14331, 0.14725, 0.13042, 0.12649, 0.44437, 0.41321, 0.3901, 0.29812, 0.29403, 0.30945, 0.10828, 0.11057, 0.11704, 0.16523, 0.35229, 0.40415, 0.29798, 0.32458, 0.31417, 0.32518, 0.29158, 0.28951, 0.19484, 0.18064, 0.17235, 0.12207, 0.11159, 0.05524, 0.01571, 0.00891, 0.00484, 0.00518, 0.00446, 0.00233, 0.00396, 0.00705, 0.0131 ], "comparison": { "original": "Se supone que es el gerente.", "retranscribed": "Y se supone que es el gerente. Hola.", "reference_tokens": [ "se", "supone", "que", "es", "el", "gerente" ], "hypothesis_tokens": [ "y", "se", "supone", "que", "es", "el", "gerente", "hola" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 2, "hits": 6, "reference_words": 6, "hypothesis_words": 8, "edits": 2 }, "wer": 0.3333333333333333, "wer_percent": 33.33333333333333, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "y", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "se", "hypothesis": "se", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "supone", "hypothesis": "supone", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "que", "hypothesis": "que", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "es", "hypothesis": "es", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "el", "hypothesis": "el", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "gerente", "hypothesis": "gerente", "reference_index": 5, "hypothesis_index": 6 }, { "op": "insert", "reference": null, "hypothesis": "hola", "reference_index": null, "hypothesis_index": 7 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.44437, "audio_sample_format": "pcm16" }, { "language": "Spanish", "emotion": "Surprised", "emotion_confidence": 0.44546204805374146, "duration_seconds": 0.5289999999999964, "mos": 3.1606, "audio_variant": "original", "original_transcript_raw": "Текса. ", "original_transcript": "Текса.", "retranscribed_transcript": "Qué cosa.", "backend": "qwen", "emotion_analyzed_seconds": 0.529, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-135", "energy": { "value": 0.703125, "bucket": "high" }, "audio_url": "audio/utterance-135.wav", "spectrogram_url": "spectrograms/utterance-135.png", "waveform": [ 0.02846, 0.04674, 0.09454, 0.07376, 0.10019, 0.1012, 0.10231, 0.09146, 0.11098, 0.13708, 0.16305, 0.17754, 0.17601, 0.19626, 0.20666, 0.19306, 0.21303, 0.20774, 0.17888, 0.12162, 0.15092, 0.10557, 0.07128, 0.05563, 0.07702, 0.06487, 0.08268, 0.05393, 0.04957, 0.04029, 0.03768, 0.05906, 0.01497, 0.03561, 0.07402, 0.07678, 0.04123, 0.05541, 0.04238, 0.07132, 0.05481, 0.06505, 0.08501, 0.0791, 0.03915, 0.10271, 0.11889, 0.15461, 0.20131, 0.27032, 0.23972, 0.35008, 0.39957, 0.42372, 0.4293, 0.37541, 0.41657, 0.41367, 0.41985, 0.42562, 0.34826, 0.4293, 0.39516, 0.37821, 0.24813, 0.38315, 0.37832, 0.35698, 0.24495, 0.31227, 0.24749, 0.18835, 0.1449, 0.10818, 0.13595, 0.08036, 0.08481, 0.07593, 0.07602, 0.05529, 0.03845, 0.04754, 0.03406, 0.02783, 0.03064, 0.04315, 0.02805, 0.03616, 0.03806, 0.03302, 0.03293, 0.0649, 0.05905, 0.05611, 0.05001, 0.03946, 0.06795, 0.07612, 0.1397, 0.15442, 0.14646, 0.15338, 0.15962, 0.19519, 0.20523, 0.18077, 0.24114, 0.17782, 0.27726, 0.15337, 0.26211, 0.14555, 0.25802, 0.15611, 0.21075, 0.1304, 0.23396, 0.11985, 0.21732, 0.09167, 0.19667, 0.06487, 0.04913, 0.12545, 0.05733, 0.08412, 0.03884, 0.02579, 0.02584, 0.02638, 0.02246, 0.0189, 0.01427, 0.00926, 0.01806, 0.01345, 0.0081, 0.0097, 0.00759, 0.00517, 0.00439, 0.00654, 0.00332, 0.00332, 0.00364, 0.00463, 0.00351, 0.00337, 0.00237, 0.00209, 0.00211, 0.00276, 0.00347, 0.00211, 0.00225, 0.00393, 0.00224, 0.00234, 0.00361, 0.00167, 0.0019, 0.0013, 0.00181, 0.00131, 0.00136, 0.00153, 0.00229, 0.00173, 0.00164, 0.0019, 0.00138, 0.00119, 0.00124, 0.00189, 0.00207, 0.00139, 0.00058, 0.00095, 0.00113, 0.00118 ], "comparison": { "original": "Текса.", "retranscribed": "Qué cosa.", "reference_tokens": [ "текса" ], "hypothesis_tokens": [ "qué", "cosa" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 1, "hits": 0, "reference_words": 1, "hypothesis_words": 2, "edits": 2 }, "wer": 2.0, "wer_percent": 200.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "qué", "reference_index": null, "hypothesis_index": 0 }, { "op": "substitute", "reference": "текса", "hypothesis": "cosa", "reference_index": 0, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.4293, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Angry", "emotion_confidence": 0.3272365629673004, "duration_seconds": 4.367999999999995, "mos": 3.1766, "audio_variant": "cleaned", "original_transcript_raw": "सब हम अपने लिए कर रहे हैं सिर्फ अपने लिए। ", "original_transcript": "सब हम अपने लिए कर रहे हैं सिर्फ अपने लिए।", "retranscribed_transcript": "ये सब हम अपने लिए कर रहे हैं सिर्फ अपने लिए", "backend": "bodhan", "emotion_analyzed_seconds": 4.368, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-136", "energy": { "value": 0.4765625, "bucket": "low" }, "audio_url": "audio/utterance-136.wav", "spectrogram_url": "spectrograms/utterance-136.png", "waveform": [ 0.06926, 0.1233, 0.13253, 0.10143, 0.05935, 0.05187, 0.06612, 0.03959, 0.04721, 0.04481, 0.04913, 0.04273, 0.04656, 0.16166, 0.22846, 0.16434, 0.17448, 0.17474, 0.09017, 0.01651, 0.00148, 0.02616, 0.01568, 0.00738, 0.00101, 0.00013, 9e-05, 0.00298, 0.02461, 0.1121, 0.20124, 0.34455, 0.27675, 0.23775, 0.15524, 0.11878, 0.09896, 0.08078, 0.08453, 0.03248, 0.00031, 0.00018, 0.00011, 7e-05, 6e-05, 0.0024, 0.26462, 0.14494, 0.07071, 0.002, 0.00017, 5e-05, 7e-05, 0.01529, 0.18659, 0.18714, 0.12617, 0.00542, 0.00157, 0.08807, 0.22888, 0.20702, 0.20812, 0.21026, 0.19551, 0.13464, 0.14361, 0.14551, 0.11448, 0.16786, 0.16826, 0.22367, 0.20721, 0.20617, 0.21667, 0.20058, 0.17211, 0.04443, 0.00445, 0.00588, 0.18777, 0.19547, 0.18837, 0.17964, 0.17552, 0.14501, 0.13054, 0.09898, 0.08253, 0.2103, 0.19757, 0.18572, 0.19644, 0.18653, 0.13873, 0.15282, 0.12765, 0.11109, 0.11, 0.10156, 0.11032, 0.10424, 0.08033, 0.05815, 0.03223, 0.05908, 0.10705, 0.11146, 0.05873, 0.04371, 0.0151, 0.00469, 0.00025, 0.0001, 7e-05, 6e-05, 5e-05, 4e-05, 5e-05, 0.00986, 0.0183, 0.02649, 0.02959, 0.03256, 0.02807, 0.02903, 0.02912, 0.02566, 0.04697, 0.11236, 0.12367, 0.08692, 0.0198, 0.02754, 0.02009, 0.00659, 0.00376, 0.00206, 0.00168, 0.00095, 0.00113, 0.00017, 6e-05, 5e-05, 4e-05, 3e-05, 0.00258, 0.32065, 0.19503, 0.11896, 0.00899, 0.0004, 0.00011, 0.00034, 0.07832, 0.15686, 0.18274, 0.18673, 0.19408, 0.21754, 0.19116, 0.16087, 0.15133, 0.1498, 0.14551, 0.12129, 0.12241, 0.15735, 0.22949, 0.21549, 0.18374, 0.18529, 0.17876, 0.19838, 0.16023, 0.13119, 0.10289, 0.06974, 0.03512, 0.02842 ], "comparison": { "original": "सब हम अपने लिए कर रहे हैं सिर्फ अपने लिए।", "retranscribed": "ये सब हम अपने लिए कर रहे हैं सिर्फ अपने लिए", "reference_tokens": [ "सब", "हम", "अपने", "लिए", "कर", "रहे", "हैं", "सिर्फ", "अपने", "लिए" ], "hypothesis_tokens": [ "ये", "सब", "हम", "अपने", "लिए", "कर", "रहे", "हैं", "सिर्फ", "अपने", "लिए" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 10, "reference_words": 10, "hypothesis_words": 11, "edits": 1 }, "wer": 0.1, "wer_percent": 10.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "ये", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "सब", "hypothesis": "सब", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "हम", "hypothesis": "हम", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "अपने", "hypothesis": "अपने", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "लिए", "hypothesis": "लिए", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "कर", "hypothesis": "कर", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "रहे", "hypothesis": "रहे", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "हैं", "hypothesis": "हैं", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "सिर्फ", "hypothesis": "सिर्फ", "reference_index": 7, "hypothesis_index": 8 }, { "op": "equal", "reference": "अपने", "hypothesis": "अपने", "reference_index": 8, "hypothesis_index": 9 }, { "op": "equal", "reference": "लिए", "hypothesis": "लिए", "reference_index": 9, "hypothesis_index": 10 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.34455, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Angry", "emotion_confidence": 0.28488847613334656, "duration_seconds": 4.282999999999959, "mos": 3.1286, "audio_variant": "cleaned", "original_transcript_raw": "बस मैं तुमसे सॉरी कहना चाहता हूँ, कहना चाहता हूँ जैसे उनमें चास", "original_transcript": "बस मैं तुमसे सॉरी कहना चाहता हूँ, कहना चाहता हूँ जैसे उनमें चास", "retranscribed_transcript": "बस मैं तुमसे सॉरी कहना चाहता हूँ कहना चाहता हूँ जस्ट वन मोर चांस", "backend": "bodhan", "emotion_analyzed_seconds": 4.283, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-137", "energy": { "value": 0.51171875, "bucket": "low" }, "audio_url": "audio/utterance-137.wav", "spectrogram_url": "spectrograms/utterance-137.png", "waveform": [ 0.08483, 0.05941, 0.00104, 0.00019, 0.00498, 0.02118, 0.03486, 0.24664, 0.27283, 0.27171, 0.27474, 0.14967, 0.08694, 0.10958, 0.07238, 0.01244, 0.15707, 0.23301, 0.23491, 0.22844, 0.11345, 0.00639, 0.13065, 0.17979, 0.20457, 0.19235, 0.18961, 0.12066, 0.09246, 0.10266, 0.22684, 0.20882, 0.13473, 0.10842, 0.11223, 0.07022, 0.07583, 0.18613, 0.22014, 0.18199, 0.21625, 0.15542, 0.20919, 0.23379, 0.18481, 0.13419, 0.0387, 0.12207, 0.17648, 0.16192, 0.16341, 0.14581, 0.16242, 0.17953, 0.15711, 0.10691, 0.02221, 0.09334, 0.10348, 0.1247, 0.1454, 0.11831, 0.10301, 0.02911, 0.07374, 0.09966, 0.09501, 0.11675, 0.04991, 0.02161, 0.00333, 0.0012, 0.00451, 0.05089, 0.03044, 0.04691, 0.04343, 0.02084, 0.02718, 0.03729, 0.04945, 0.009, 0.00125, 0.02663, 0.04289, 0.01636, 0.02771, 0.01564, 0.00599, 0.00102, 0.00034, 0.00024, 0.00021, 0.00016, 0.00011, 7e-05, 6e-05, 6e-05, 7e-05, 5e-05, 6e-05, 5e-05, 6e-05, 6e-05, 5e-05, 5e-05, 5e-05, 5e-05, 7e-05, 9e-05, 9e-05, 0.00016, 0.00014, 0.00028, 0.00048, 0.00044, 0.0004, 0.00037, 0.00047, 0.00048, 0.00036, 0.00043, 0.0004, 0.00028, 0.00015, 7e-05, 7e-05, 0.00455, 0.08989, 0.10224, 0.13369, 0.14113, 0.10126, 0.09052, 0.09422, 0.08543, 0.17043, 0.20252, 0.20948, 0.19028, 0.1966, 0.18168, 0.17997, 0.15535, 0.13883, 0.04153, 0.09996, 0.1379, 0.15914, 0.1643, 0.16033, 0.13398, 0.06091, 0.01294, 0.08572, 0.06373, 0.07232, 0.0825, 0.08321, 0.04789, 0.01815, 0.00179, 0.0003, 0.00018, 0.00017, 0.00011, 7e-05, 7e-05, 6e-05, 8e-05, 8e-05, 0.00014, 0.00192, 0.00301, 0.00373, 0.00224, 0.00132, 0.00806, 0.05252, 0.13145 ], "comparison": { "original": "बस मैं तुमसे सॉरी कहना चाहता हूँ, कहना चाहता हूँ जैसे उनमें चास", "retranscribed": "बस मैं तुमसे सॉरी कहना चाहता हूँ कहना चाहता हूँ जस्ट वन मोर चांस", "reference_tokens": [ "बस", "मैं", "तुमसे", "सॉरी", "कहना", "चाहता", "हूँ", "कहना", "चाहता", "हूँ", "जैसे", "उनमें", "चास" ], "hypothesis_tokens": [ "बस", "मैं", "तुमसे", "सॉरी", "कहना", "चाहता", "हूँ", "कहना", "चाहता", "हूँ", "जस्ट", "वन", "मोर", "चांस" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 1, "hits": 10, "reference_words": 13, "hypothesis_words": 14, "edits": 4 }, "wer": 0.3076923076923077, "wer_percent": 30.76923076923077, "alignment": [ { "op": "equal", "reference": "बस", "hypothesis": "बस", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "तुमसे", "hypothesis": "तुमसे", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "सॉरी", "hypothesis": "सॉरी", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "कहना", "hypothesis": "कहना", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "चाहता", "hypothesis": "चाहता", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "हूँ", "hypothesis": "हूँ", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "कहना", "hypothesis": "कहना", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "चाहता", "hypothesis": "चाहता", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "हूँ", "hypothesis": "हूँ", "reference_index": 9, "hypothesis_index": 9 }, { "op": "insert", "reference": null, "hypothesis": "जस्ट", "reference_index": null, "hypothesis_index": 10 }, { "op": "substitute", "reference": "जैसे", "hypothesis": "वन", "reference_index": 10, "hypothesis_index": 11 }, { "op": "substitute", "reference": "उनमें", "hypothesis": "मोर", "reference_index": 11, "hypothesis_index": 12 }, { "op": "substitute", "reference": "चास", "hypothesis": "चांस", "reference_index": 12, "hypothesis_index": 13 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.27474, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Angry", "emotion_confidence": 0.28744110465049744, "duration_seconds": 4.130000000000052, "mos": 3.1434, "audio_variant": "cleaned", "original_transcript_raw": "बस मैं तुमसे सॉरी कहना चाहता हूँ कहना चाहता जिस वन में चांस. ", "original_transcript": "बस मैं तुमसे सॉरी कहना चाहता हूँ कहना चाहता जिस वन में चांस.", "retranscribed_transcript": "बस मैं तुमसे सॉरी कहना चाहता हूँ कहना चाहता हूँ जस्ट वन मच आन्स", "backend": "bodhan", "emotion_analyzed_seconds": 4.13, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-138", "energy": { "value": 0.51171875, "bucket": "low" }, "audio_url": "audio/utterance-138.wav", "spectrogram_url": "spectrograms/utterance-138.png", "waveform": [ 0.07094, 0.02846, 0.00519, 0.00172, 0.08997, 0.28176, 0.27803, 0.27371, 0.21578, 0.07214, 0.07182, 0.09891, 0.04449, 0.01387, 0.19995, 0.22394, 0.19599, 0.22535, 0.10237, 0.00993, 0.14018, 0.19386, 0.20892, 0.18954, 0.19207, 0.14177, 0.08395, 0.11524, 0.1774, 0.22904, 0.15781, 0.10039, 0.09857, 0.07441, 0.06937, 0.0728, 0.20444, 0.17134, 0.18556, 0.20032, 0.1358, 0.23047, 0.22063, 0.16392, 0.07618, 0.07665, 0.12706, 0.19081, 0.1925, 0.20076, 0.16812, 0.15073, 0.1699, 0.16339, 0.11558, 0.04856, 0.08943, 0.11835, 0.14875, 0.14403, 0.16337, 0.1158, 0.06759, 0.01447, 0.06797, 0.1191, 0.10211, 0.12046, 0.0377, 0.01816, 0.00304, 0.00129, 0.00737, 0.03546, 0.03659, 0.05463, 0.04699, 0.03679, 0.01092, 0.0368, 0.03797, 0.01143, 0.00213, 0.01041, 0.03276, 0.01954, 0.01803, 0.0181, 0.0032, 0.00098, 0.0004, 0.00033, 0.00025, 0.00019, 0.00018, 9e-05, 6e-05, 7e-05, 7e-05, 6e-05, 6e-05, 6e-05, 5e-05, 5e-05, 5e-05, 5e-05, 5e-05, 5e-05, 5e-05, 7e-05, 0.00013, 0.00025, 0.00029, 0.0004, 0.00041, 0.00067, 0.00057, 0.0007, 0.00054, 0.00058, 0.00062, 0.00064, 0.00052, 0.00048, 0.00047, 0.00023, 0.00013, 8e-05, 8e-05, 0.00174, 0.09062, 0.0927, 0.10445, 0.14265, 0.1291, 0.11216, 0.10488, 0.11699, 0.16391, 0.19934, 0.21852, 0.20885, 0.19976, 0.20592, 0.17801, 0.17602, 0.18338, 0.14898, 0.12861, 0.10797, 0.13998, 0.16901, 0.16429, 0.13266, 0.12504, 0.05564, 0.03039, 0.05372, 0.07366, 0.08668, 0.08125, 0.08446, 0.04489, 0.0203, 0.0042, 0.00038, 0.00019, 0.00012, 7e-05, 7e-05, 6e-05, 5e-05, 4e-05, 5e-05, 6e-05, 0.00174, 0.00243, 0.00577, 0.07956, 0.1915 ], "comparison": { "original": "बस मैं तुमसे सॉरी कहना चाहता हूँ कहना चाहता जिस वन में चांस.", "retranscribed": "बस मैं तुमसे सॉरी कहना चाहता हूँ कहना चाहता हूँ जस्ट वन मच आन्स", "reference_tokens": [ "बस", "मैं", "तुमसे", "सॉरी", "कहना", "चाहता", "हूँ", "कहना", "चाहता", "जिस", "वन", "में", "चांस" ], "hypothesis_tokens": [ "बस", "मैं", "तुमसे", "सॉरी", "कहना", "चाहता", "हूँ", "कहना", "चाहता", "हूँ", "जस्ट", "वन", "मच", "आन्स" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 1, "hits": 10, "reference_words": 13, "hypothesis_words": 14, "edits": 4 }, "wer": 0.3076923076923077, "wer_percent": 30.76923076923077, "alignment": [ { "op": "equal", "reference": "बस", "hypothesis": "बस", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "तुमसे", "hypothesis": "तुमसे", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "सॉरी", "hypothesis": "सॉरी", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "कहना", "hypothesis": "कहना", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "चाहता", "hypothesis": "चाहता", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "हूँ", "hypothesis": "हूँ", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "कहना", "hypothesis": "कहना", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "चाहता", "hypothesis": "चाहता", "reference_index": 8, "hypothesis_index": 8 }, { "op": "insert", "reference": null, "hypothesis": "हूँ", "reference_index": null, "hypothesis_index": 9 }, { "op": "substitute", "reference": "जिस", "hypothesis": "जस्ट", "reference_index": 9, "hypothesis_index": 10 }, { "op": "equal", "reference": "वन", "hypothesis": "वन", "reference_index": 10, "hypothesis_index": 11 }, { "op": "substitute", "reference": "में", "hypothesis": "मच", "reference_index": 11, "hypothesis_index": 12 }, { "op": "substitute", "reference": "चांस", "hypothesis": "आन्स", "reference_index": 12, "hypothesis_index": 13 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.28176, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Angry", "emotion_confidence": 0.3853803277015686, "duration_seconds": 4.283999999999992, "mos": 2.8711, "audio_variant": "cleaned", "original_transcript_raw": "Que najá bala", "original_transcript": "Que najá bala", "retranscribed_transcript": "कहो नानक जीअड़ा बलिहारी", "backend": "bodhan", "emotion_analyzed_seconds": 4.284, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-139", "energy": { "value": 0.5390625, "bucket": "medium" }, "audio_url": "audio/utterance-139.wav", "spectrogram_url": "spectrograms/utterance-139.png", "waveform": [ 0.16821, 0.25857, 0.30777, 0.33691, 0.42289, 0.46662, 0.47708, 0.47858, 0.36882, 0.34827, 0.42521, 0.5057, 0.49889, 0.35338, 0.30388, 0.21045, 0.21686, 0.21967, 0.24958, 0.43202, 0.40097, 0.37511, 0.41495, 0.45363, 0.48941, 0.39319, 0.40424, 0.47722, 0.49293, 0.5125, 0.45014, 0.38061, 0.27813, 0.20304, 0.20211, 0.25397, 0.37653, 0.40354, 0.48922, 0.48886, 0.32691, 0.1035, 0.01266, 0.0027, 0.05637, 0.13562, 0.35345, 0.45907, 0.46942, 0.36654, 0.33876, 0.33415, 0.32621, 0.30806, 0.283, 0.30333, 0.31169, 0.2818, 0.28497, 0.25025, 0.25564, 0.27079, 0.27025, 0.25958, 0.23302, 0.2805, 0.24445, 0.24761, 0.23239, 0.24194, 0.24769, 0.24376, 0.23467, 0.22186, 0.25192, 0.23401, 0.23353, 0.23219, 0.23213, 0.22787, 0.23477, 0.23857, 0.24583, 0.24739, 0.24466, 0.24631, 0.28298, 0.38918, 0.25528, 0.11841, 0.06047, 0.05724, 0.05185, 0.08395, 0.15589, 0.26124, 0.28412, 0.28374, 0.28802, 0.25212, 0.30289, 0.41836, 0.51583, 0.55437, 0.58244, 0.57638, 0.44462, 0.42855, 0.51008, 0.45112, 0.45712, 0.46686, 0.44099, 0.43968, 0.4624, 0.43985, 0.43511, 0.43341, 0.39348, 0.35, 0.33646, 0.34729, 0.29224, 0.30037, 0.20511, 0.12451, 0.11768, 0.09954, 0.415, 0.56254, 0.48602, 0.44603, 0.47218, 0.57018, 0.36635, 0.33582, 0.3016, 0.36683, 0.48367, 0.52451, 0.55872, 0.58341, 0.39224, 0.2143, 0.20055, 0.34469, 0.46792, 0.47577, 0.4559, 0.43213, 0.41192, 0.39502, 0.36081, 0.34486, 0.31017, 0.31095, 0.31636, 0.32946, 0.3205, 0.36268, 0.25871, 0.41983, 0.40474, 0.31905, 0.30533, 0.24608, 0.22418, 0.24848, 0.28882, 0.25253, 0.22316, 0.18932, 0.22808, 0.17562, 0.14733, 0.10294, 0.09913, 0.03544, 0.05018, 0.04896 ], "comparison": { "original": "Que najá bala", "retranscribed": "कहो नानक जीअड़ा बलिहारी", "reference_tokens": [ "que", "najá", "bala" ], "hypothesis_tokens": [ "कहो", "नानक", "जीअड़ा", "बलिहारी" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 1, "hits": 0, "reference_words": 3, "hypothesis_words": 4, "edits": 4 }, "wer": 1.3333333333333333, "wer_percent": 133.33333333333331, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "कहो", "reference_index": null, "hypothesis_index": 0 }, { "op": "substitute", "reference": "que", "hypothesis": "नानक", "reference_index": 0, "hypothesis_index": 1 }, { "op": "substitute", "reference": "najá", "hypothesis": "जीअड़ा", "reference_index": 1, "hypothesis_index": 2 }, { "op": "substitute", "reference": "bala", "hypothesis": "बलिहारी", "reference_index": 2, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.58341, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Angry", "emotion_confidence": 0.25900742411613464, "duration_seconds": 3.3279999999999745, "mos": 3.27, "audio_variant": "cleaned", "original_transcript_raw": "रवि उसका क्या, उसके बारे में तुमने नहीं सोचा माँ? ", "original_transcript": "रवि उसका क्या, उसके बारे में तुमने नहीं सोचा माँ?", "retranscribed_transcript": "रवि उसका क्या उसके बारे में तुमने नहीं सोचा माँ", "backend": "bodhan", "emotion_analyzed_seconds": 3.328, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-140", "energy": { "value": 0.5703125, "bucket": "medium" }, "audio_url": "audio/utterance-140.wav", "spectrogram_url": "spectrograms/utterance-140.png", "waveform": [ 0.30625, 0.07126, 0.05216, 0.07217, 0.12228, 0.19642, 0.24927, 0.30607, 0.30921, 0.18591, 0.0524, 0.06944, 0.42789, 0.44798, 0.35781, 0.26638, 0.12477, 0.03088, 0.0072, 0.00107, 0.0016, 0.00124, 0.00096, 0.00106, 0.00086, 0.00082, 0.0008, 0.00078, 0.00173, 0.00087, 0.00103, 0.00155, 0.0008, 0.0011, 0.00113, 0.00096, 0.00111, 0.00092, 0.00068, 0.00114, 0.00096, 0.00075, 0.00117, 0.00111, 0.00139, 0.00121, 0.00101, 0.00088, 0.00065, 0.00051, 0.00091, 0.00123, 0.00102, 0.23488, 0.2709, 0.27568, 0.1276, 0.11663, 0.07682, 0.02008, 0.21775, 0.47817, 0.58872, 0.49455, 0.41464, 0.13156, 0.00908, 0.00199, 0.10256, 0.06196, 0.13545, 0.11983, 0.10419, 0.08114, 0.06229, 0.03665, 0.02402, 0.01179, 0.00405, 0.00186, 0.00169, 0.00173, 0.00175, 0.00113, 0.00095, 0.00282, 0.00137, 0.00169, 0.00158, 0.00178, 0.00169, 0.00168, 0.0018, 0.00245, 0.00181, 0.00269, 0.00302, 0.00111, 0.00173, 0.00188, 0.00172, 0.00133, 0.00132, 0.00141, 0.0006, 0.00099, 0.00109, 0.03427, 0.0337, 0.26371, 0.28155, 0.14159, 0.1294, 0.08186, 0.10339, 0.10723, 0.45761, 0.6878, 0.54951, 0.17816, 0.44955, 0.58038, 0.53485, 0.49448, 0.43324, 0.31277, 0.37617, 0.42378, 0.50081, 0.5134, 0.42817, 0.12967, 0.00741, 0.12001, 0.3993, 0.45989, 0.46215, 0.54548, 0.58818, 0.59978, 0.66219, 0.66461, 0.6498, 0.53842, 0.55182, 0.52072, 0.41569, 0.36857, 0.37612, 0.44082, 0.58795, 0.55736, 0.43464, 0.16258, 0.12516, 0.29481, 0.37895, 0.34385, 0.20346, 0.01362, 0.12577, 0.15221, 0.28321, 0.29516, 0.32166, 0.31781, 0.32746, 0.28324, 0.27214, 0.29928, 0.29641, 0.22944, 0.21894, 0.14012, 0.10164, 0.02158, 0.00351, 0.00916, 0.02949, 0.08075 ], "comparison": { "original": "रवि उसका क्या, उसके बारे में तुमने नहीं सोचा माँ?", "retranscribed": "रवि उसका क्या उसके बारे में तुमने नहीं सोचा माँ", "reference_tokens": [ "रवि", "उसका", "क्या", "उसके", "बारे", "में", "तुमने", "नहीं", "सोचा", "माँ" ], "hypothesis_tokens": [ "रवि", "उसका", "क्या", "उसके", "बारे", "में", "तुमने", "नहीं", "सोचा", "माँ" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 10, "reference_words": 10, "hypothesis_words": 10, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "रवि", "hypothesis": "रवि", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "उसका", "hypothesis": "उसका", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "क्या", "hypothesis": "क्या", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "उसके", "hypothesis": "उसके", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "बारे", "hypothesis": "बारे", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "में", "hypothesis": "में", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "तुमने", "hypothesis": "तुमने", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "नहीं", "hypothesis": "नहीं", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "सोचा", "hypothesis": "सोचा", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "माँ", "hypothesis": "माँ", "reference_index": 9, "hypothesis_index": 9 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.6878, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Angry", "emotion_confidence": 0.36842143535614014, "duration_seconds": 1.075000000000017, "mos": 3.2185, "audio_variant": "cleaned", "original_transcript_raw": "बताइए मैंने किया क्या है? ", "original_transcript": "बताइए मैंने किया क्या है?", "retranscribed_transcript": "बताइए मैंने किया क्या है", "backend": "bodhan", "emotion_analyzed_seconds": 1.075, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-141", "energy": { "value": 0.56640625, "bucket": "medium" }, "audio_url": "audio/utterance-141.wav", "spectrogram_url": "spectrograms/utterance-141.png", "waveform": [ 0.37486, 0.24742, 0.21666, 0.26929, 0.1591, 0.17848, 0.14495, 0.19095, 0.34353, 0.33296, 0.50914, 0.40903, 0.58409, 0.51565, 0.44834, 0.4385, 0.40933, 0.37039, 0.29326, 0.25051, 0.13555, 0.12178, 0.07947, 0.02158, 0.12086, 0.18056, 0.31728, 0.33171, 0.22129, 0.59422, 0.5018, 0.50433, 0.54927, 0.49862, 0.53737, 0.52226, 0.49666, 0.50364, 0.38964, 0.31582, 0.33024, 0.32138, 0.36881, 0.4033, 0.30969, 0.31186, 0.30751, 0.37663, 0.30116, 0.4053, 0.37809, 0.33546, 0.35584, 0.31391, 0.33882, 0.34946, 0.26733, 0.27302, 0.25304, 0.21298, 0.22536, 0.2489, 0.22399, 0.22726, 0.27169, 0.25657, 0.30019, 0.38557, 0.39206, 0.46477, 0.47252, 0.43682, 0.49843, 0.45808, 0.47611, 0.50371, 0.28679, 0.36474, 0.39062, 0.26971, 0.41009, 0.43388, 0.3556, 0.45803, 0.49335, 0.32339, 0.4294, 0.36991, 0.32692, 0.37227, 0.22425, 0.22915, 0.19307, 0.11164, 0.05279, 0.0527, 0.01765, 0.01149, 0.00788, 0.00501, 0.04497, 0.10424, 0.05782, 0.0341, 0.10676, 0.0927, 0.06324, 0.0798, 0.05531, 0.07287, 0.06482, 0.25976, 0.25392, 0.40901, 0.35516, 0.32464, 0.37819, 0.37396, 0.35634, 0.52219, 0.3745, 0.42756, 0.43224, 0.44673, 0.37791, 0.45069, 0.33565, 0.3345, 0.21901, 0.16654, 0.14425, 0.15294, 0.13759, 0.09652, 0.02564, 0.01718, 0.00833, 0.00634, 0.00178, 0.00131, 0.00086, 0.00219, 0.00591, 0.12238, 0.16753, 0.1297, 0.08831, 0.05012, 0.06192, 0.03911, 0.05288, 0.07774, 0.35024, 0.3728, 0.30914, 0.43822, 0.31691, 0.47354, 0.34347, 0.45953, 0.32168, 0.31469, 0.36381, 0.28839, 0.37435, 0.23626, 0.24949, 0.16955, 0.17385, 0.10643, 0.15967, 0.10434, 0.07488, 0.11405, 0.15711, 0.12501, 0.12713, 0.24343, 0.15792, 0.20847 ], "comparison": { "original": "बताइए मैंने किया क्या है?", "retranscribed": "बताइए मैंने किया क्या है", "reference_tokens": [ "बताइए", "मैंने", "किया", "क्या", "है" ], "hypothesis_tokens": [ "बताइए", "मैंने", "किया", "क्या", "है" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 5, "hypothesis_words": 5, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "बताइए", "hypothesis": "बताइए", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "मैंने", "hypothesis": "मैंने", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "किया", "hypothesis": "किया", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "क्या", "hypothesis": "क्या", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.59422, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Angry", "emotion_confidence": 0.24784158170223236, "duration_seconds": 1.1779999999999973, "mos": 3.0847, "audio_variant": "original", "original_transcript_raw": "ये कैसे पागल पड़ेगा? ", "original_transcript": "ये कैसे पागल पड़ेगा?", "retranscribed_transcript": "ये कैसा पागलपन है चुप कर", "backend": "bodhan", "emotion_analyzed_seconds": 1.178, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-142", "energy": { "value": 0.68359375, "bucket": "high" }, "audio_url": "audio/utterance-142.wav", "spectrogram_url": "spectrograms/utterance-142.png", "waveform": [ 0.24878, 0.34274, 0.55072, 0.63292, 0.67303, 0.48263, 0.64654, 0.55183, 0.59294, 0.52414, 0.40136, 0.33325, 0.17643, 0.27799, 0.20462, 0.13994, 0.0942, 0.09255, 0.12207, 0.08831, 0.13017, 0.21385, 0.28928, 0.46071, 0.53303, 0.6252, 0.58102, 0.56073, 0.45803, 0.49023, 0.42255, 0.42354, 0.28311, 0.26146, 0.28941, 0.19231, 0.17215, 0.23335, 0.27755, 0.5546, 0.46629, 0.47159, 0.39679, 0.52844, 0.46465, 0.42232, 0.26264, 0.14198, 0.14281, 0.15837, 0.07436, 0.07158, 0.09993, 0.09608, 0.10699, 0.20034, 0.20185, 0.28748, 0.47754, 0.48127, 0.35693, 0.24473, 0.18033, 0.17788, 0.18811, 0.18032, 0.13866, 0.19176, 0.14783, 0.22174, 0.35583, 0.53186, 0.47465, 0.58112, 0.45042, 0.30638, 0.28229, 0.27967, 0.28607, 0.2389, 0.18309, 0.18685, 0.17562, 0.12794, 0.13624, 0.08956, 0.07425, 0.09223, 0.06405, 0.0731, 0.44485, 0.55526, 0.39692, 0.31921, 0.36323, 0.20999, 0.1484, 0.1716, 0.08951, 0.10529, 0.09212, 0.13998, 0.17458, 0.26234, 0.31973, 0.18429, 0.20174, 0.11274, 0.09345, 0.10021, 0.10456, 0.09401, 0.06732, 0.04434, 0.08142, 0.06789, 0.03515, 0.0624, 0.05636, 0.04798, 0.03987, 0.04204, 0.43374, 0.55066, 0.55519, 0.49765, 0.51804, 0.5494, 0.55263, 0.53626, 0.38052, 0.42845, 0.44817, 0.393, 0.32133, 0.36632, 0.40569, 0.26472, 0.33025, 0.32448, 0.34543, 0.40552, 0.29212, 0.36895, 0.31163, 0.30727, 0.24629, 0.23386, 0.15558, 0.25083, 0.11782, 0.13835, 0.44704, 0.43835, 0.40042, 0.51678, 0.50941, 0.34988, 0.35031, 0.17308, 0.16057, 0.13919, 0.13983, 0.14131, 0.07272, 0.08336, 0.09672, 0.06366, 0.05657, 0.23555, 0.30302, 0.238, 0.23444, 0.29875, 0.53266, 0.38477, 0.50009, 0.57242, 0.5215, 0.39581 ], "comparison": { "original": "ये कैसे पागल पड़ेगा?", "retranscribed": "ये कैसा पागलपन है चुप कर", "reference_tokens": [ "ये", "कैसे", "पागल", "पड़ेगा" ], "hypothesis_tokens": [ "ये", "कैसा", "पागलपन", "है", "चुप", "कर" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 2, "hits": 1, "reference_words": 4, "hypothesis_words": 6, "edits": 5 }, "wer": 1.25, "wer_percent": 125.0, "alignment": [ { "op": "equal", "reference": "ये", "hypothesis": "ये", "reference_index": 0, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "कैसा", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "पागलपन", "reference_index": null, "hypothesis_index": 2 }, { "op": "substitute", "reference": "कैसे", "hypothesis": "है", "reference_index": 1, "hypothesis_index": 3 }, { "op": "substitute", "reference": "पागल", "hypothesis": "चुप", "reference_index": 2, "hypothesis_index": 4 }, { "op": "substitute", "reference": "पड़ेगा", "hypothesis": "कर", "reference_index": 3, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.67303, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Angry", "emotion_confidence": 0.3193037509918213, "duration_seconds": 1.7410000000000139, "mos": 3.4453, "audio_variant": "cleaned", "original_transcript_raw": "Я дика фри ай чекникам. ", "original_transcript": "Я дика фри ай чекникам.", "retranscribed_transcript": "ये सी आई डी का फ्री आई चेकिंग कैंप है", "backend": "bodhan", "emotion_analyzed_seconds": 1.741, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-143", "energy": { "value": 0.66015625, "bucket": "high" }, "audio_url": "audio/utterance-143.wav", "spectrogram_url": "spectrograms/utterance-143.png", "waveform": [ 0.95166, 0.80331, 0.95831, 0.80507, 0.56791, 0.36857, 0.20364, 0.13488, 0.1121, 0.0802, 0.07462, 0.09261, 0.08494, 0.0795, 0.05574, 0.25839, 0.41604, 0.53956, 0.60682, 0.65679, 0.74884, 0.731, 0.7164, 0.9722, 1.00948, 1.02049, 1.04643, 1.03404, 0.95261, 0.79684, 0.8477, 0.89835, 0.78473, 0.40894, 0.18922, 0.19163, 0.14465, 0.84243, 1.04411, 1.01314, 1.06131, 0.89524, 0.79032, 0.45154, 0.22048, 0.1876, 0.20499, 0.3293, 0.75779, 1.03278, 1.03812, 0.99761, 1.00541, 1.0003, 0.74478, 0.30893, 0.10148, 0.07101, 0.02952, 0.0269, 0.03516, 0.05323, 0.04416, 0.04316, 0.20286, 0.56075, 0.73296, 0.71606, 0.36571, 0.76306, 0.95881, 0.82944, 0.72083, 0.6823, 0.62051, 0.6495, 0.66612, 0.75457, 0.78967, 0.73277, 0.7222, 0.93572, 0.99838, 0.9878, 1.00427, 1.01595, 1.02053, 0.79335, 0.66265, 0.64083, 0.64406, 0.62159, 0.46157, 0.28007, 0.12664, 0.06837, 0.02453, 0.02778, 0.09505, 0.07906, 0.14724, 0.40047, 0.58258, 0.6962, 0.67416, 0.59922, 0.33527, 0.12859, 0.08859, 0.06701, 0.0549, 0.13873, 0.73323, 1.00106, 1.02234, 1.00708, 0.99655, 0.92345, 0.5837, 0.40294, 0.36163, 0.35832, 0.34006, 0.28604, 0.1881, 0.17155, 0.09351, 0.10211, 0.30643, 0.59861, 0.93209, 1.02202, 0.98919, 1.01626, 1.02367, 1.02688, 1.00154, 1.00537, 1.01904, 1.01044, 1.01025, 0.74327, 0.33019, 0.32035, 0.26481, 0.20337, 0.11094, 0.0614, 0.03213, 0.03274, 0.0208, 0.13486, 0.46836, 0.64589, 0.67746, 0.54395, 0.83656, 0.6787, 0.39988, 0.41488, 0.3607, 0.2308, 0.18123, 0.10959, 0.04251, 0.03319, 0.02258, 0.01019, 0.01375, 0.01204, 0.00521, 0.00643, 0.00551, 0.00369, 0.0056, 0.02507, 0.06218, 0.06805, 0.1082, 0.10544 ], "comparison": { "original": "Я дика фри ай чекникам.", "retranscribed": "ये सी आई डी का फ्री आई चेकिंग कैंप है", "reference_tokens": [ "я", "дика", "фри", "ай", "чекникам" ], "hypothesis_tokens": [ "ये", "सी", "आई", "डी", "का", "फ्री", "आई", "चेकिंग", "कैंप", "है" ], "counts": { "substitutions": 5, "deletions": 0, "insertions": 5, "hits": 0, "reference_words": 5, "hypothesis_words": 10, "edits": 10 }, "wer": 2.0, "wer_percent": 200.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "ये", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "सी", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "आई", "reference_index": null, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "डी", "reference_index": null, "hypothesis_index": 3 }, { "op": "insert", "reference": null, "hypothesis": "का", "reference_index": null, "hypothesis_index": 4 }, { "op": "substitute", "reference": "я", "hypothesis": "फ्री", "reference_index": 0, "hypothesis_index": 5 }, { "op": "substitute", "reference": "дика", "hypothesis": "आई", "reference_index": 1, "hypothesis_index": 6 }, { "op": "substitute", "reference": "фри", "hypothesis": "चेकिंग", "reference_index": 2, "hypothesis_index": 7 }, { "op": "substitute", "reference": "ай", "hypothesis": "कैंप", "reference_index": 3, "hypothesis_index": 8 }, { "op": "substitute", "reference": "чекникам", "hypothesis": "है", "reference_index": 4, "hypothesis_index": 9 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz float32 WAV", "source_peak_abs": 1.06131, "audio_sample_format": "float32" }, { "language": "Hindi", "emotion": "Angry", "emotion_confidence": 0.5255917906761169, "duration_seconds": 1.4839999999999804, "mos": 3.7959, "audio_variant": "cleaned", "original_transcript_raw": "साले मैं धूम कर लाया था वो। ", "original_transcript": "साले मैं धूम कर लाया था वो।", "retranscribed_transcript": "साले मैं ढूंढ कर लाया था वो", "backend": "bodhan", "emotion_analyzed_seconds": 1.484, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-144", "energy": { "value": 0.7109375, "bucket": "high" }, "audio_url": "audio/utterance-144.wav", "spectrogram_url": "spectrograms/utterance-144.png", "waveform": [ 0.06657, 0.07785, 0.06967, 0.05659, 0.04272, 0.04258, 0.0472, 0.04408, 0.04636, 0.05701, 0.05788, 0.03226, 0.22544, 0.41265, 0.41854, 0.3872, 0.35004, 0.40807, 0.40167, 0.43358, 0.26258, 0.25449, 0.25507, 0.25966, 0.25835, 0.36686, 0.37399, 0.36385, 0.36642, 0.35392, 0.22204, 0.21531, 0.19815, 0.20285, 0.21648, 0.22776, 0.24905, 0.23504, 0.22638, 0.22179, 0.39164, 0.50197, 0.57843, 0.4667, 0.51649, 0.4699, 0.4983, 0.47536, 0.44196, 0.35004, 0.23042, 0.20704, 0.12151, 0.05678, 0.04758, 0.05065, 0.03197, 0.06215, 0.06219, 0.21265, 0.34738, 0.38158, 0.34578, 0.30689, 0.25427, 0.17182, 0.16197, 0.16397, 0.11958, 0.10688, 0.11803, 0.12239, 0.13656, 0.21963, 0.1154, 0.10991, 0.11729, 0.11268, 0.15099, 0.21802, 0.31305, 0.30385, 0.32981, 0.39793, 0.40779, 0.38203, 0.20562, 0.15707, 0.19094, 0.21265, 0.24904, 0.2452, 0.25035, 0.29718, 0.34872, 0.49965, 0.45264, 0.35744, 0.27836, 0.2761, 0.25027, 0.25875, 0.2771, 0.29049, 0.20581, 0.11444, 0.05296, 0.03231, 0.02397, 0.03571, 0.04186, 0.12596, 0.20612, 0.25774, 0.29829, 0.26872, 0.26368, 0.20587, 0.19192, 0.13995, 0.1155, 0.09762, 0.12973, 0.13788, 0.15247, 0.14293, 0.1428, 0.14329, 0.13459, 0.1151, 0.08906, 0.07016, 0.06081, 0.04598, 0.03108, 0.01824, 0.00917, 0.00853, 0.0053, 0.00597, 0.00528, 0.00257, 0.0026, 0.00264, 0.00307, 0.00204, 0.00199, 0.00137, 0.00099, 0.00045, 0.00065, 0.00048, 0.00051, 0.00017, 0.00023, 0.00015, 0.00016, 9e-05, 9e-05, 6e-05, 5e-05, 4e-05, 5e-05, 4e-05, 5e-05, 4e-05, 4e-05, 4e-05, 3e-05, 4e-05, 3e-05, 3e-05, 5e-05, 0.0001, 0.00069, 0.00126, 0.00286, 0.00476, 0.00442, 0.00647 ], "comparison": { "original": "साले मैं धूम कर लाया था वो।", "retranscribed": "साले मैं ढूंढ कर लाया था वो", "reference_tokens": [ "साले", "मैं", "धूम", "कर", "लाया", "था", "वो" ], "hypothesis_tokens": [ "साले", "मैं", "ढूंढ", "कर", "लाया", "था", "वो" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 6, "reference_words": 7, "hypothesis_words": 7, "edits": 1 }, "wer": 0.14285714285714285, "wer_percent": 14.285714285714285, "alignment": [ { "op": "equal", "reference": "साले", "hypothesis": "साले", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "धूम", "hypothesis": "ढूंढ", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "कर", "hypothesis": "कर", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "लाया", "hypothesis": "लाया", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "था", "hypothesis": "था", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "वो", "hypothesis": "वो", "reference_index": 6, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.57843, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Annoyed", "emotion_confidence": 0.2628617584705353, "duration_seconds": 4.957, "mos": 2.8975, "audio_variant": "cleaned", "original_transcript_raw": "मुझसे फिर नहीं मिलना। तुम्हारी एक फूल से मेरी खुशकिस्मती", "original_transcript": "मुझसे फिर नहीं मिलना। तुम्हारी एक फूल से मेरी खुशकिस्मती", "retranscribed_transcript": "मुझसे फिर नहीं मिलना तुम्हारी एक भूल से मेरी खुशकिस्मती", "backend": "bodhan", "emotion_analyzed_seconds": 4.957, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-145", "energy": { "value": 0.494140625, "bucket": "low" }, "audio_url": "audio/utterance-145.wav", "spectrogram_url": "spectrograms/utterance-145.png", "waveform": [ 0.00044, 0.00071, 0.00052, 0.00079, 0.00232, 0.08064, 0.30075, 0.36137, 0.17096, 0.21612, 0.16998, 0.03194, 0.03471, 0.01617, 0.03857, 0.26899, 0.42433, 0.17419, 0.00589, 0.00114, 0.04367, 0.08232, 0.12507, 0.41001, 0.36628, 0.13073, 0.19606, 0.26925, 0.29276, 0.22653, 0.21306, 0.19231, 0.16571, 0.15739, 0.20784, 0.24018, 0.2199, 0.18505, 0.15992, 0.16954, 0.16802, 0.126, 0.08961, 0.12001, 0.16362, 0.14771, 0.1345, 0.04909, 0.03443, 0.01696, 0.00221, 0.00221, 0.00242, 0.00324, 0.00271, 0.00204, 0.00192, 0.00159, 0.00204, 0.0011, 0.00118, 0.00092, 0.00143, 0.00099, 0.00081, 0.0011, 0.00076, 0.00089, 0.00071, 0.00049, 0.00044, 0.00026, 0.00034, 0.00032, 0.00029, 0.00027, 0.0003, 0.00037, 0.00036, 0.09392, 0.29952, 0.31553, 0.32703, 0.20024, 0.18532, 0.21269, 0.29466, 0.30695, 0.22474, 0.25391, 0.26586, 0.25525, 0.21475, 0.30931, 0.46319, 0.50631, 0.40462, 0.25393, 0.09467, 0.00446, 0.03946, 0.04328, 0.04313, 0.15965, 0.15545, 0.14487, 0.11788, 0.09693, 0.05099, 0.04504, 0.02601, 0.04846, 0.10845, 0.11284, 0.09638, 0.05962, 0.03292, 0.01184, 0.00194, 0.00674, 0.00833, 0.01144, 0.00658, 0.00454, 0.00493, 0.00538, 0.00449, 0.00291, 0.00234, 0.00131, 0.00092, 0.00092, 0.00087, 0.00073, 0.00053, 0.00063, 0.00051, 0.00069, 0.02619, 0.02446, 0.05026, 0.20173, 0.28719, 0.31493, 0.3139, 0.30447, 0.29283, 0.40723, 0.23579, 0.10876, 0.0455, 0.07285, 0.09206, 0.1531, 0.28319, 0.24989, 0.11301, 0.16514, 0.13509, 0.01934, 0.19497, 0.28377, 0.1851, 0.02208, 0.01025, 0.03415, 0.01686, 0.18853, 0.18853, 0.22302, 0.03622, 0.00167, 0.02738, 0.09602, 0.09603, 0.06656, 0.00797, 0.00784, 0.00795, 0.01531 ], "comparison": { "original": "मुझसे फिर नहीं मिलना। तुम्हारी एक फूल से मेरी खुशकिस्मती", "retranscribed": "मुझसे फिर नहीं मिलना तुम्हारी एक भूल से मेरी खुशकिस्मती", "reference_tokens": [ "मुझसे", "फिर", "नहीं", "मिलना", "तुम्हारी", "एक", "फूल", "से", "मेरी", "खुशकिस्मती" ], "hypothesis_tokens": [ "मुझसे", "फिर", "नहीं", "मिलना", "तुम्हारी", "एक", "भूल", "से", "मेरी", "खुशकिस्मती" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 9, "reference_words": 10, "hypothesis_words": 10, "edits": 1 }, "wer": 0.1, "wer_percent": 10.0, "alignment": [ { "op": "equal", "reference": "मुझसे", "hypothesis": "मुझसे", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "फिर", "hypothesis": "फिर", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "नहीं", "hypothesis": "नहीं", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "मिलना", "hypothesis": "मिलना", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "तुम्हारी", "hypothesis": "तुम्हारी", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "एक", "hypothesis": "एक", "reference_index": 5, "hypothesis_index": 5 }, { "op": "substitute", "reference": "फूल", "hypothesis": "भूल", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "से", "hypothesis": "से", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "मेरी", "hypothesis": "मेरी", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "खुशकिस्मती", "hypothesis": "खुशकिस्मती", "reference_index": 9, "hypothesis_index": 9 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.50631, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Annoyed", "emotion_confidence": 0.270357608795166, "duration_seconds": 4.060999999999979, "mos": 3.0775, "audio_variant": "cleaned", "original_transcript_raw": "मैं उनसे बहुत प्यार करना चाहता हूँ लेकिन भरोसा ही नहीं कर पाता। ", "original_transcript": "मैं उनसे बहुत प्यार करना चाहता हूँ लेकिन भरोसा ही नहीं कर पाता।", "retranscribed_transcript": "सर मैं उनसे बहुत प्यार करना चाहता हूँ लेकिन भरोसा ही नहीं कर पाता", "backend": "bodhan", "emotion_analyzed_seconds": 4.061, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-146", "energy": { "value": 0.51171875, "bucket": "low" }, "audio_url": "audio/utterance-146.wav", "spectrogram_url": "spectrograms/utterance-146.png", "waveform": [ 0.06083, 0.31722, 0.29498, 0.20427, 0.21494, 0.19485, 0.16284, 0.16603, 0.17265, 0.1793, 0.18221, 0.17705, 0.14075, 0.13446, 0.07745, 0.0439, 0.05885, 0.23291, 0.2078, 0.11427, 0.09182, 0.20188, 0.23026, 0.22242, 0.26293, 0.25539, 0.17994, 0.04356, 0.00729, 0.00043, 0.06765, 0.25865, 0.28696, 0.28329, 0.24233, 0.18806, 0.07741, 0.04919, 0.13478, 0.20661, 0.22446, 0.12989, 0.11762, 0.10347, 0.10553, 0.08461, 0.0473, 0.04751, 0.05439, 0.17166, 0.13515, 0.10082, 0.04652, 0.01468, 0.00232, 0.05845, 0.07273, 0.10762, 0.09781, 0.07032, 0.04253, 0.04125, 0.02454, 0.01673, 0.00981, 0.00669, 0.00239, 0.00031, 0.00015, 7e-05, 6e-05, 5e-05, 4e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 2e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 6e-05, 0.00878, 0.16256, 0.16552, 0.16308, 0.04311, 0.13803, 0.10235, 0.178, 0.17464, 0.18148, 0.16525, 0.12176, 0.12343, 0.1704, 0.1515, 0.13306, 0.1042, 0.17656, 0.18112, 0.17584, 0.16141, 0.08063, 0.04395, 0.04345, 0.21685, 0.25897, 0.21314, 0.1788, 0.15584, 0.1494, 0.18233, 0.16544, 0.0643, 0.10043, 0.16619, 0.21386, 0.19884, 0.14263, 0.09, 0.02848, 0.00763, 0.10022, 0.19662, 0.1306, 0.07298, 0.01711, 0.00173, 0.09246, 0.0656, 0.09027, 0.06775, 0.07216, 0.03593, 0.02038, 0.0095, 0.00413, 0.00057, 0.00015, 0.0001, 6e-05, 5e-05, 4e-05, 3e-05, 4e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 2e-05, 2e-05, 2e-05, 5e-05, 4e-05, 4e-05, 4e-05, 3e-05, 3e-05, 2e-05, 2e-05, 0.00305, 0.02411, 0.04593 ], "comparison": { "original": "मैं उनसे बहुत प्यार करना चाहता हूँ लेकिन भरोसा ही नहीं कर पाता।", "retranscribed": "सर मैं उनसे बहुत प्यार करना चाहता हूँ लेकिन भरोसा ही नहीं कर पाता", "reference_tokens": [ "मैं", "उनसे", "बहुत", "प्यार", "करना", "चाहता", "हूँ", "लेकिन", "भरोसा", "ही", "नहीं", "कर", "पाता" ], "hypothesis_tokens": [ "सर", "मैं", "उनसे", "बहुत", "प्यार", "करना", "चाहता", "हूँ", "लेकिन", "भरोसा", "ही", "नहीं", "कर", "पाता" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 13, "reference_words": 13, "hypothesis_words": 14, "edits": 1 }, "wer": 0.07692307692307693, "wer_percent": 7.6923076923076925, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "सर", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "उनसे", "hypothesis": "उनसे", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "बहुत", "hypothesis": "बहुत", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "प्यार", "hypothesis": "प्यार", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "करना", "hypothesis": "करना", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "चाहता", "hypothesis": "चाहता", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "हूँ", "hypothesis": "हूँ", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "लेकिन", "hypothesis": "लेकिन", "reference_index": 7, "hypothesis_index": 8 }, { "op": "equal", "reference": "भरोसा", "hypothesis": "भरोसा", "reference_index": 8, "hypothesis_index": 9 }, { "op": "equal", "reference": "ही", "hypothesis": "ही", "reference_index": 9, "hypothesis_index": 10 }, { "op": "equal", "reference": "नहीं", "hypothesis": "नहीं", "reference_index": 10, "hypothesis_index": 11 }, { "op": "equal", "reference": "कर", "hypothesis": "कर", "reference_index": 11, "hypothesis_index": 12 }, { "op": "equal", "reference": "पाता", "hypothesis": "पाता", "reference_index": 12, "hypothesis_index": 13 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.31722, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Annoyed", "emotion_confidence": 0.4416444003582001, "duration_seconds": 1.3479999999999848, "mos": 3.1738, "audio_variant": "cleaned", "original_transcript_raw": "mood नहीं है मेरे को। ", "original_transcript": "mood नहीं है मेरे को।", "retranscribed_transcript": "मूड नहीं है विभू", "backend": "bodhan", "emotion_analyzed_seconds": 1.348, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-147", "energy": { "value": 0.51171875, "bucket": "low" }, "audio_url": "audio/utterance-147.wav", "spectrogram_url": "spectrograms/utterance-147.png", "waveform": [ 0.00437, 0.00218, 0.00696, 0.02518, 0.03292, 0.01289, 0.0265, 0.00952, 0.0279, 0.04405, 0.08249, 0.10479, 0.12235, 0.17075, 0.14806, 0.16373, 0.17553, 0.17292, 0.18968, 0.20384, 0.20344, 0.253, 0.26506, 0.28289, 0.29182, 0.31786, 0.32677, 0.33239, 0.34728, 0.37197, 0.39223, 0.43662, 0.47964, 0.50572, 0.48391, 0.50885, 0.53167, 0.54717, 0.49469, 0.51096, 0.42332, 0.39731, 0.2627, 0.15166, 0.1009, 0.08306, 0.05315, 0.04341, 0.03369, 0.02934, 0.02545, 0.02437, 0.04275, 0.07069, 0.10663, 0.15247, 0.16397, 0.18893, 0.20339, 0.21111, 0.21191, 0.22989, 0.22395, 0.22672, 0.23105, 0.2366, 0.23296, 0.25467, 0.44419, 0.4271, 0.53558, 0.57858, 0.55798, 0.592, 0.58803, 0.55374, 0.59298, 0.63388, 0.6879, 0.67003, 0.60325, 0.57345, 0.58864, 0.49913, 0.44333, 0.41498, 0.39637, 0.35362, 0.33945, 0.3155, 0.34792, 0.36639, 0.39871, 0.43082, 0.54269, 0.57697, 0.63954, 0.65467, 0.70039, 0.72517, 0.69128, 0.77185, 0.76388, 0.74476, 0.57768, 0.48118, 0.29168, 0.23369, 0.18632, 0.16454, 0.15526, 0.15029, 0.20423, 0.21093, 0.25562, 0.2929, 0.31764, 0.35868, 0.46192, 0.54428, 0.5066, 0.47923, 0.38652, 0.26768, 0.20561, 0.13377, 0.10655, 0.092, 0.0521, 0.01658, 0.01634, 0.0065, 0.00192, 0.00109, 0.00062, 0.00057, 0.00188, 0.01475, 0.0578, 0.13264, 0.27763, 0.29477, 0.3066, 0.29615, 0.28247, 0.28208, 0.28284, 0.25381, 0.24924, 0.26375, 0.26265, 0.258, 0.25636, 0.21763, 0.17512, 0.16897, 0.04161, 0.13896, 0.05865, 0.03235, 0.12579, 0.00903, 0.0239, 0.0737, 0.00751, 0.00544, 0.00177, 0.00438, 0.01211, 0.00251, 0.00051, 0.00098, 0.00235, 0.00246, 0.00556, 0.01126, 0.01441, 0.04097, 0.03976, 0.04046 ], "comparison": { "original": "mood नहीं है मेरे को।", "retranscribed": "मूड नहीं है विभू", "reference_tokens": [ "mood", "नहीं", "है", "मेरे", "को" ], "hypothesis_tokens": [ "मूड", "नहीं", "है", "विभू" ], "counts": { "substitutions": 2, "deletions": 1, "insertions": 0, "hits": 2, "reference_words": 5, "hypothesis_words": 4, "edits": 3 }, "wer": 0.6, "wer_percent": 60.0, "alignment": [ { "op": "substitute", "reference": "mood", "hypothesis": "मूड", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "नहीं", "hypothesis": "नहीं", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 2, "hypothesis_index": 2 }, { "op": "delete", "reference": "मेरे", "hypothesis": null, "reference_index": 3, "hypothesis_index": null }, { "op": "substitute", "reference": "को", "hypothesis": "विभू", "reference_index": 4, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.77185, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Annoyed", "emotion_confidence": 0.3275512456893921, "duration_seconds": 2.6789999999999736, "mos": 3.0627, "audio_variant": "cleaned", "original_transcript_raw": "कुछ बात करनी थी, मैं अपना बिज़नस शुरू कर रही हूँ। ", "original_transcript": "कुछ बात करनी थी, मैं अपना बिज़नस शुरू कर रही हूँ।", "retranscribed_transcript": "कुछ बात करनी थी मैं अपना बिज़नेस शुरू कर रही हूँ", "backend": "bodhan", "emotion_analyzed_seconds": 2.679, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-148", "energy": { "value": 0.57421875, "bucket": "medium" }, "audio_url": "audio/utterance-148.wav", "spectrogram_url": "spectrograms/utterance-148.png", "waveform": [ 0.1751, 0.03699, 0.23665, 0.24889, 0.06067, 0.00459, 0.00178, 0.01552, 0.03359, 0.09023, 0.05697, 0.02042, 0.00423, 0.00052, 0.00091, 0.00093, 0.00148, 0.0347, 0.53135, 0.61969, 0.66278, 0.60104, 0.32815, 0.37532, 0.26082, 0.22052, 0.22664, 0.0319, 0.00429, 0.00148, 0.00112, 0.00078, 0.0009, 0.04331, 0.01773, 0.00091, 0.0008, 0.00108, 0.12424, 0.33689, 0.42425, 0.33766, 0.28577, 0.10777, 0.18003, 0.22318, 0.21829, 0.22839, 0.22771, 0.23818, 0.1991, 0.17763, 0.14615, 0.12681, 0.08028, 0.03752, 0.07259, 0.06069, 0.02273, 0.02454, 0.13068, 0.12544, 0.10314, 0.08837, 0.07206, 0.02946, 0.00554, 0.00313, 0.00167, 0.00094, 0.0012, 0.00069, 0.00076, 0.00197, 0.06557, 0.1807, 0.1908, 0.23889, 0.25157, 0.38132, 0.42267, 0.4483, 0.44144, 0.35405, 0.21971, 0.4983, 0.51249, 0.44513, 0.26131, 0.21198, 0.01537, 0.00346, 0.00455, 0.01172, 0.01838, 0.24237, 0.31729, 0.2943, 0.42817, 0.37276, 0.33496, 0.35428, 0.36825, 0.13183, 0.1086, 0.08663, 0.07709, 0.29246, 0.39464, 0.3828, 0.29689, 0.11732, 0.06968, 0.02775, 0.05059, 0.15456, 0.21991, 0.25153, 0.28807, 0.36191, 0.33421, 0.30193, 0.17559, 0.05559, 0.07531, 0.11263, 0.07862, 0.07204, 0.05793, 0.0575, 0.24913, 0.25767, 0.23232, 0.20339, 0.30574, 0.28527, 0.22251, 0.16697, 0.04214, 0.00942, 0.00261, 0.19625, 0.41963, 0.33817, 0.38416, 0.39433, 0.35863, 0.09246, 0.05547, 0.06668, 0.03596, 0.13668, 0.2073, 0.25604, 0.25765, 0.2268, 0.20799, 0.19078, 0.15414, 0.15013, 0.14342, 0.12349, 0.11442, 0.1127, 0.11372, 0.12503, 0.13166, 0.12806, 0.08471, 0.04942, 0.0152, 0.00553, 0.0042, 0.00422, 0.00249, 0.00254, 0.00439, 0.02573, 0.04151, 0.06739 ], "comparison": { "original": "कुछ बात करनी थी, मैं अपना बिज़नस शुरू कर रही हूँ।", "retranscribed": "कुछ बात करनी थी मैं अपना बिज़नेस शुरू कर रही हूँ", "reference_tokens": [ "कुछ", "बात", "करनी", "थी", "मैं", "अपना", "बिज़नस", "शुरू", "कर", "रही", "हूँ" ], "hypothesis_tokens": [ "कुछ", "बात", "करनी", "थी", "मैं", "अपना", "बिज़नेस", "शुरू", "कर", "रही", "हूँ" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 10, "reference_words": 11, "hypothesis_words": 11, "edits": 1 }, "wer": 0.09090909090909091, "wer_percent": 9.090909090909092, "alignment": [ { "op": "equal", "reference": "कुछ", "hypothesis": "कुछ", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "बात", "hypothesis": "बात", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "करनी", "hypothesis": "करनी", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "थी", "hypothesis": "थी", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "अपना", "hypothesis": "अपना", "reference_index": 5, "hypothesis_index": 5 }, { "op": "substitute", "reference": "बिज़नस", "hypothesis": "बिज़नेस", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "शुरू", "hypothesis": "शुरू", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "कर", "hypothesis": "कर", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "रही", "hypothesis": "रही", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "हूँ", "hypothesis": "हूँ", "reference_index": 10, "hypothesis_index": 10 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.66278, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Annoyed", "emotion_confidence": 0.2967351973056793, "duration_seconds": 5.546999999999997, "mos": 3.2501, "audio_variant": "cleaned", "original_transcript_raw": "बहुत बड़े सर्जन ने मुझसे कहा था कि कभी कभी पेशेंट की भलाई के लिए तफकॉज के", "original_transcript": "बहुत बड़े सर्जन ने मुझसे कहा था कि कभी कभी पेशेंट की भलाई के लिए तफकॉज के", "retranscribed_transcript": "किसी बहुत बड़े सर्जन ने मुझसे कहा था कि कभी कभी पेशेंट की भलाई के लिए टफ कॉल्स देने पड़ते हैं", "backend": "bodhan", "emotion_analyzed_seconds": 5.547, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-149", "energy": { "value": 0.5234375, "bucket": "medium" }, "audio_url": "audio/utterance-149.wav", "spectrogram_url": "spectrograms/utterance-149.png", "waveform": [ 0.21945, 0.01478, 0.1066, 0.22751, 0.20349, 0.10134, 0.19257, 0.24339, 0.2502, 0.32272, 0.27623, 0.22547, 0.07017, 0.20783, 0.25036, 0.22061, 0.22602, 0.21644, 0.19227, 0.08157, 0.0105, 0.01016, 0.20041, 0.21367, 0.21286, 0.20734, 0.09277, 0.06963, 0.21234, 0.20699, 0.15638, 0.12855, 0.22825, 0.25129, 0.14499, 0.14763, 0.17447, 0.18382, 0.03868, 0.01618, 0.03129, 0.16474, 0.18698, 0.20422, 0.09658, 0.24166, 0.33683, 0.32303, 0.28388, 0.16862, 0.00587, 0.08583, 0.04369, 0.03232, 0.00518, 9e-05, 9e-05, 6e-05, 5e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 0.00065, 0.19994, 0.22582, 0.17945, 0.10938, 0.27424, 0.24786, 0.17274, 0.11369, 0.15638, 0.13959, 0.02736, 0.12985, 0.21434, 0.18111, 0.07897, 0.15105, 0.15757, 0.14921, 0.05873, 0.00118, 0.20222, 0.20313, 0.17847, 0.1407, 0.06149, 0.05197, 0.16698, 0.15129, 0.11121, 0.09152, 0.08678, 0.18387, 0.17862, 0.08975, 0.10011, 0.11821, 0.10817, 0.14957, 0.2226, 0.27254, 0.24866, 0.24193, 0.20857, 0.18573, 0.1199, 0.00238, 0.04755, 0.1709, 0.17268, 0.16274, 0.07112, 0.05958, 0.07675, 0.06683, 0.05998, 0.03717, 0.00643, 0.00038, 9e-05, 8e-05, 5e-05, 4e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 3e-05, 4e-05, 2e-05, 3e-05, 3e-05, 5e-05, 0.28245, 0.28988, 0.2163, 0.05377, 0.03691, 0.05613, 0.04608, 0.00369, 0.26715, 0.29575, 0.30404, 0.31089, 0.22415, 0.1775, 0.09719, 0.03727, 0.02388, 0.0153, 0.00299, 0.2114, 0.21315, 0.12621, 0.10999, 0.09696, 0.10329, 0.06341, 0.00112, 0.21172, 0.17182 ], "comparison": { "original": "बहुत बड़े सर्जन ने मुझसे कहा था कि कभी कभी पेशेंट की भलाई के लिए तफकॉज के", "retranscribed": "किसी बहुत बड़े सर्जन ने मुझसे कहा था कि कभी कभी पेशेंट की भलाई के लिए टफ कॉल्स देने पड़ते हैं", "reference_tokens": [ "बहुत", "बड़े", "सर्जन", "ने", "मुझसे", "कहा", "था", "कि", "कभी", "कभी", "पेशेंट", "की", "भलाई", "के", "लिए", "तफकॉज", "के" ], "hypothesis_tokens": [ "किसी", "बहुत", "बड़े", "सर्जन", "ने", "मुझसे", "कहा", "था", "कि", "कभी", "कभी", "पेशेंट", "की", "भलाई", "के", "लिए", "टफ", "कॉल्स", "देने", "पड़ते", "हैं" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 4, "hits": 15, "reference_words": 17, "hypothesis_words": 21, "edits": 6 }, "wer": 0.35294117647058826, "wer_percent": 35.294117647058826, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "किसी", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "बहुत", "hypothesis": "बहुत", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "बड़े", "hypothesis": "बड़े", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "सर्जन", "hypothesis": "सर्जन", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "ने", "hypothesis": "ने", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "मुझसे", "hypothesis": "मुझसे", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "कहा", "hypothesis": "कहा", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "था", "hypothesis": "था", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "कि", "hypothesis": "कि", "reference_index": 7, "hypothesis_index": 8 }, { "op": "equal", "reference": "कभी", "hypothesis": "कभी", "reference_index": 8, "hypothesis_index": 9 }, { "op": "equal", "reference": "कभी", "hypothesis": "कभी", "reference_index": 9, "hypothesis_index": 10 }, { "op": "equal", "reference": "पेशेंट", "hypothesis": "पेशेंट", "reference_index": 10, "hypothesis_index": 11 }, { "op": "equal", "reference": "की", "hypothesis": "की", "reference_index": 11, "hypothesis_index": 12 }, { "op": "equal", "reference": "भलाई", "hypothesis": "भलाई", "reference_index": 12, "hypothesis_index": 13 }, { "op": "equal", "reference": "के", "hypothesis": "के", "reference_index": 13, "hypothesis_index": 14 }, { "op": "equal", "reference": "लिए", "hypothesis": "लिए", "reference_index": 14, "hypothesis_index": 15 }, { "op": "insert", "reference": null, "hypothesis": "टफ", "reference_index": null, "hypothesis_index": 16 }, { "op": "insert", "reference": null, "hypothesis": "कॉल्स", "reference_index": null, "hypothesis_index": 17 }, { "op": "insert", "reference": null, "hypothesis": "देने", "reference_index": null, "hypothesis_index": 18 }, { "op": "substitute", "reference": "तफकॉज", "hypothesis": "पड़ते", "reference_index": 15, "hypothesis_index": 19 }, { "op": "substitute", "reference": "के", "hypothesis": "हैं", "reference_index": 16, "hypothesis_index": 20 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.33683, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Annoyed", "emotion_confidence": 0.3901687562465668, "duration_seconds": 4.231999999999971, "mos": 3.4277, "audio_variant": "cleaned", "original_transcript_raw": "तो ऐसा लगता है जैसे भूलेना चाहिए, कोई संकेत देना चाह रहा है. ", "original_transcript": "तो ऐसा लगता है जैसे भूलेना चाहिए, कोई संकेत देना चाह रहा है.", "retranscribed_transcript": "तो ऐसे लगता है जैसे भोलेनाथ जी कोई संकेत देना चाह रहे हैं", "backend": "bodhan", "emotion_analyzed_seconds": 4.232, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-150", "energy": { "value": 0.53125, "bucket": "medium" }, "audio_url": "audio/utterance-150.wav", "spectrogram_url": "spectrograms/utterance-150.png", "waveform": [ 0.01144, 0.06485, 0.29564, 0.25709, 0.28233, 0.26282, 0.26964, 0.24341, 0.14917, 0.04445, 0.0417, 0.04586, 0.0374, 0.31669, 0.29748, 0.23408, 0.17681, 0.18949, 0.20241, 0.28496, 0.2522, 0.036, 0.00285, 0.00045, 0.00021, 0.00023, 0.00019, 9e-05, 0.12486, 0.14931, 0.22304, 0.20878, 0.199, 0.19692, 0.213, 0.24231, 0.25002, 0.23185, 0.21422, 0.17119, 0.09856, 0.07753, 0.09149, 0.19803, 0.2029, 0.18806, 0.13635, 0.07764, 0.05144, 0.03362, 0.04696, 0.0477, 0.08627, 0.25318, 0.21392, 0.2192, 0.19194, 0.13962, 0.00775, 0.0001, 9e-05, 8e-05, 7e-05, 6e-05, 6e-05, 5e-05, 4e-05, 4e-05, 4e-05, 4e-05, 3e-05, 4e-05, 3e-05, 0.00204, 0.11584, 0.0989, 0.05359, 0.0071, 0.13454, 0.18535, 0.18816, 0.13125, 0.24883, 0.2872, 0.24056, 0.22247, 0.25703, 0.25827, 0.19815, 0.18312, 0.07836, 0.12006, 0.18535, 0.21065, 0.20769, 0.19553, 0.20145, 0.12065, 0.01624, 0.01061, 0.07072, 0.0956, 0.24225, 0.21225, 0.06899, 0.0091, 0.01117, 0.18134, 0.22029, 0.19107, 0.18533, 0.14413, 0.06723, 0.05019, 0.04917, 0.01972, 0.04203, 0.26672, 0.26758, 0.1831, 0.12169, 0.10663, 0.06972, 0.01459, 0.01148, 0.00844, 0.07569, 0.08403, 0.17871, 0.19191, 0.17275, 0.19073, 0.18775, 0.08354, 0.016, 0.00904, 0.00881, 0.00775, 0.00607, 0.22838, 0.22991, 0.17991, 0.15947, 0.13634, 0.12656, 0.13588, 0.15199, 0.14067, 0.11481, 0.05228, 0.0066, 0.0561, 0.10122, 0.05558, 0.2222, 0.2036, 0.23521, 0.2206, 0.22585, 0.22144, 0.18464, 0.1416, 0.0957, 0.08225, 0.04532, 0.0863, 0.17574, 0.16309, 0.14038, 0.1306, 0.1189, 0.07674, 0.01741, 0.01018, 0.00877, 0.00599, 0.00553, 0.00452, 0.01106, 0.05397 ], "comparison": { "original": "तो ऐसा लगता है जैसे भूलेना चाहिए, कोई संकेत देना चाह रहा है.", "retranscribed": "तो ऐसे लगता है जैसे भोलेनाथ जी कोई संकेत देना चाह रहे हैं", "reference_tokens": [ "तो", "ऐसा", "लगता", "है", "जैसे", "भूलेना", "चाहिए", "कोई", "संकेत", "देना", "चाह", "रहा", "है" ], "hypothesis_tokens": [ "तो", "ऐसे", "लगता", "है", "जैसे", "भोलेनाथ", "जी", "कोई", "संकेत", "देना", "चाह", "रहे", "हैं" ], "counts": { "substitutions": 5, "deletions": 0, "insertions": 0, "hits": 8, "reference_words": 13, "hypothesis_words": 13, "edits": 5 }, "wer": 0.38461538461538464, "wer_percent": 38.46153846153847, "alignment": [ { "op": "equal", "reference": "तो", "hypothesis": "तो", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "ऐसा", "hypothesis": "ऐसे", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "लगता", "hypothesis": "लगता", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "जैसे", "hypothesis": "जैसे", "reference_index": 4, "hypothesis_index": 4 }, { "op": "substitute", "reference": "भूलेना", "hypothesis": "भोलेनाथ", "reference_index": 5, "hypothesis_index": 5 }, { "op": "substitute", "reference": "चाहिए", "hypothesis": "जी", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "कोई", "hypothesis": "कोई", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "संकेत", "hypothesis": "संकेत", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "देना", "hypothesis": "देना", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "चाह", "hypothesis": "चाह", "reference_index": 10, "hypothesis_index": 10 }, { "op": "substitute", "reference": "रहा", "hypothesis": "रहे", "reference_index": 11, "hypothesis_index": 11 }, { "op": "substitute", "reference": "है", "hypothesis": "हैं", "reference_index": 12, "hypothesis_index": 12 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.31669, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Annoyed", "emotion_confidence": 0.3072144687175751, "duration_seconds": 1.603999999999985, "mos": 3.4657, "audio_variant": "original", "original_transcript_raw": "थोड़ा गाबा जा क्या लिया तो लग गयी तुम्हारी", "original_transcript": "थोड़ा गाबा जा क्या लिया तो लग गयी तुम्हारी", "retranscribed_transcript": "थोड़ा गा बजा के आ लिए सुलग गई तुम्हारी", "backend": "bodhan", "emotion_analyzed_seconds": 1.604, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-151", "energy": { "value": 0.66015625, "bucket": "high" }, "audio_url": "audio/utterance-151.wav", "spectrogram_url": "spectrograms/utterance-151.png", "waveform": [ 0.10874, 0.12843, 0.19789, 0.35426, 0.35342, 0.33024, 0.33749, 0.35494, 0.38605, 0.4537, 0.48258, 0.42421, 0.39305, 0.25165, 0.11707, 0.08533, 0.07079, 0.06629, 0.06323, 0.18012, 0.36687, 0.36513, 0.40611, 0.49892, 0.52137, 0.65284, 0.69218, 0.68, 0.6514, 0.61033, 0.62942, 0.09851, 0.10162, 0.08456, 0.24011, 0.29464, 0.37458, 0.56968, 0.52513, 0.51566, 0.42092, 0.39718, 0.30015, 0.13709, 0.14385, 0.13099, 0.20976, 0.38073, 0.4344, 0.45395, 0.53127, 0.48382, 0.48177, 0.46892, 0.40202, 0.4338, 0.16609, 0.06146, 0.04112, 0.02987, 0.03817, 0.0347, 0.03256, 0.06315, 0.2499, 0.35397, 0.39174, 0.41367, 0.49073, 0.356, 0.31184, 0.35719, 0.25659, 0.13748, 0.12062, 0.10556, 0.11728, 0.15889, 0.23925, 0.25325, 0.23454, 0.23362, 0.27364, 0.35022, 0.39831, 0.37264, 0.33456, 0.31641, 0.28158, 0.20837, 0.18558, 0.1157, 0.04632, 0.01215, 0.00814, 0.00588, 0.00613, 0.0115, 0.01168, 0.00901, 0.00713, 0.00679, 0.00762, 0.00726, 0.00443, 0.00429, 0.00414, 0.0059, 0.0057, 0.0093, 0.01814, 0.02567, 0.03163, 0.03444, 0.04444, 0.12565, 0.31007, 0.41667, 0.35952, 0.25565, 0.32625, 0.33949, 0.52794, 0.49792, 0.52847, 0.44291, 0.21117, 0.15181, 0.11813, 0.11029, 0.09519, 0.07097, 0.06234, 0.05126, 0.15936, 0.27369, 0.42153, 0.42762, 0.37765, 0.38887, 0.40816, 0.39692, 0.22934, 0.13479, 0.07954, 0.04371, 0.01428, 0.08517, 0.16962, 0.40076, 0.43544, 0.44779, 0.37002, 0.26536, 0.28667, 0.38026, 0.38899, 0.44612, 0.49298, 0.38739, 0.27148, 0.2882, 0.30417, 0.22189, 0.15602, 0.05446, 0.07624, 0.14172, 0.15835, 0.15553, 0.10787, 0.08647, 0.07041, 0.06296, 0.0479, 0.04079, 0.03008, 0.02609, 0.02588, 0.0191 ], "comparison": { "original": "थोड़ा गाबा जा क्या लिया तो लग गयी तुम्हारी", "retranscribed": "थोड़ा गा बजा के आ लिए सुलग गई तुम्हारी", "reference_tokens": [ "थोड़ा", "गाबा", "जा", "क्या", "लिया", "तो", "लग", "गयी", "तुम्हारी" ], "hypothesis_tokens": [ "थोड़ा", "गा", "बजा", "के", "आ", "लिए", "सुलग", "गई", "तुम्हारी" ], "counts": { "substitutions": 7, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 9, "hypothesis_words": 9, "edits": 7 }, "wer": 0.7777777777777778, "wer_percent": 77.77777777777779, "alignment": [ { "op": "equal", "reference": "थोड़ा", "hypothesis": "थोड़ा", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "गाबा", "hypothesis": "गा", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "जा", "hypothesis": "बजा", "reference_index": 2, "hypothesis_index": 2 }, { "op": "substitute", "reference": "क्या", "hypothesis": "के", "reference_index": 3, "hypothesis_index": 3 }, { "op": "substitute", "reference": "लिया", "hypothesis": "आ", "reference_index": 4, "hypothesis_index": 4 }, { "op": "substitute", "reference": "तो", "hypothesis": "लिए", "reference_index": 5, "hypothesis_index": 5 }, { "op": "substitute", "reference": "लग", "hypothesis": "सुलग", "reference_index": 6, "hypothesis_index": 6 }, { "op": "substitute", "reference": "गयी", "hypothesis": "गई", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "तुम्हारी", "hypothesis": "तुम्हारी", "reference_index": 8, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.69218, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Annoyed", "emotion_confidence": 0.5765904188156128, "duration_seconds": 3.7200000000000273, "mos": 2.9476, "audio_variant": "cleaned", "original_transcript_raw": "कोई ना कोई तुझे अच्छा नरका मिल जाएगा, जरुर मिल जाएगा अच्छी", "original_transcript": "कोई ना कोई तुझे अच्छा नरका मिल जाएगा, जरुर मिल जाएगा अच्छी", "retranscribed_transcript": "कोई ना कोई तुझे अच्छा लड़का मिल जाएगा ज़रूर मिल जाएगा ची", "backend": "bodhan", "emotion_analyzed_seconds": 3.72, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-152", "energy": { "value": 0.625, "bucket": "high" }, "audio_url": "audio/utterance-152.wav", "spectrogram_url": "spectrograms/utterance-152.png", "waveform": [ 0.03642, 0.02488, 0.00419, 0.06559, 0.19772, 0.40095, 0.43719, 0.50112, 0.44383, 0.3365, 0.34456, 0.33611, 0.35372, 0.24227, 0.25563, 0.3914, 0.41465, 0.40586, 0.23169, 0.01094, 0.0028, 0.02783, 0.26224, 0.31079, 0.33008, 0.33598, 0.31034, 0.34526, 0.32431, 0.08265, 0.00812, 0.00208, 0.0773, 0.27901, 0.30854, 0.29617, 0.15494, 0.11459, 0.24627, 0.33837, 0.37536, 0.4695, 0.18703, 0.01462, 0.00248, 0.00064, 0.00073, 0.45029, 0.23139, 0.32888, 0.08404, 0.00664, 0.01178, 0.06908, 0.06188, 0.15254, 0.21004, 0.23536, 0.2468, 0.19519, 0.11162, 0.13673, 0.18934, 0.27434, 0.39538, 0.42444, 0.14725, 0.06994, 0.00569, 0.00289, 0.08867, 0.15385, 0.24713, 0.25134, 0.26376, 0.20746, 0.19474, 0.16965, 0.25197, 0.28859, 0.26872, 0.14828, 0.15256, 0.11501, 0.04606, 0.04423, 0.04066, 0.14327, 0.15328, 0.16403, 0.15492, 0.14158, 0.10131, 0.02733, 0.02573, 0.12924, 0.10127, 0.1162, 0.09505, 0.07308, 0.02139, 0.0027, 0.01869, 0.01605, 0.01201, 0.01032, 0.01143, 0.05871, 0.0847, 0.06908, 0.06898, 0.09439, 0.26735, 0.43482, 0.44181, 0.34179, 0.56585, 0.45654, 0.41733, 0.52729, 0.58537, 0.54938, 0.32309, 0.24554, 0.27628, 0.27751, 0.36498, 0.58248, 0.54837, 0.43882, 0.36036, 0.25351, 0.19323, 0.12429, 0.251, 0.46619, 0.48531, 0.58375, 0.59731, 0.48566, 0.22066, 0.16076, 0.42364, 0.4012, 0.40462, 0.29454, 0.07557, 0.01172, 0.02492, 0.06069, 0.08134, 0.07685, 0.05189, 0.15301, 0.24069, 0.26824, 0.25218, 0.26026, 0.28831, 0.29338, 0.28506, 0.32376, 0.30892, 0.30364, 0.28512, 0.24454, 0.26296, 0.29031, 0.24603, 0.16649, 0.08162, 0.02723, 0.01072, 0.00488, 0.00186, 0.00089, 0.00033, 0.03844, 0.1227, 0.22568 ], "comparison": { "original": "कोई ना कोई तुझे अच्छा नरका मिल जाएगा, जरुर मिल जाएगा अच्छी", "retranscribed": "कोई ना कोई तुझे अच्छा लड़का मिल जाएगा ज़रूर मिल जाएगा ची", "reference_tokens": [ "कोई", "ना", "कोई", "तुझे", "अच्छा", "नरका", "मिल", "जाएगा", "जरुर", "मिल", "जाएगा", "अच्छी" ], "hypothesis_tokens": [ "कोई", "ना", "कोई", "तुझे", "अच्छा", "लड़का", "मिल", "जाएगा", "ज़रूर", "मिल", "जाएगा", "ची" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 0, "hits": 9, "reference_words": 12, "hypothesis_words": 12, "edits": 3 }, "wer": 0.25, "wer_percent": 25.0, "alignment": [ { "op": "equal", "reference": "कोई", "hypothesis": "कोई", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "ना", "hypothesis": "ना", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "कोई", "hypothesis": "कोई", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "तुझे", "hypothesis": "तुझे", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "अच्छा", "hypothesis": "अच्छा", "reference_index": 4, "hypothesis_index": 4 }, { "op": "substitute", "reference": "नरका", "hypothesis": "लड़का", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "मिल", "hypothesis": "मिल", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "जाएगा", "hypothesis": "जाएगा", "reference_index": 7, "hypothesis_index": 7 }, { "op": "substitute", "reference": "जरुर", "hypothesis": "ज़रूर", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "मिल", "hypothesis": "मिल", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "जाएगा", "hypothesis": "जाएगा", "reference_index": 10, "hypothesis_index": 10 }, { "op": "substitute", "reference": "अच्छी", "hypothesis": "ची", "reference_index": 11, "hypothesis_index": 11 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.59731, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Annoyed", "emotion_confidence": 0.29923367500305176, "duration_seconds": 2.61099999999999, "mos": 3.2993, "audio_variant": "cleaned", "original_transcript_raw": "लेकिन अगर इसे हम ध्यान से देखेंगे। ", "original_transcript": "लेकिन अगर इसे हम ध्यान से देखेंगे।", "retranscribed_transcript": "लेकिन अगर इसे हम ध्यान से देखेंगे", "backend": "bodhan", "emotion_analyzed_seconds": 2.611, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-153", "energy": { "value": 0.6328125, "bucket": "high" }, "audio_url": "audio/utterance-153.wav", "spectrogram_url": "spectrograms/utterance-153.png", "waveform": [ 0.01791, 0.02142, 0.27256, 0.32508, 1.02324, 1.062, 1.02794, 0.90894, 0.16455, 0.01828, 0.01484, 0.14761, 0.12588, 0.47079, 0.70908, 0.66524, 0.37404, 0.38447, 0.73857, 0.81254, 0.64681, 0.39559, 0.43475, 0.86996, 1.05164, 1.02407, 0.99822, 0.29356, 0.17652, 0.14856, 0.48223, 0.95321, 1.00851, 0.86131, 0.75768, 0.73106, 0.46513, 0.21898, 0.1017, 0.00825, 0.00755, 0.0198, 0.19425, 0.40278, 0.49745, 0.47025, 0.35331, 0.16412, 0.12773, 0.09284, 0.0573, 0.03773, 0.0275, 0.03793, 0.07181, 0.54978, 0.9601, 1.01317, 1.07047, 0.94191, 0.68452, 0.43972, 0.30009, 0.31919, 0.33544, 0.46113, 0.32191, 0.27783, 0.2358, 0.44311, 0.66026, 0.80697, 0.80971, 0.69695, 0.26597, 0.25561, 0.24207, 0.21312, 0.2038, 0.14713, 0.09267, 0.02892, 0.00719, 0.00239, 0.00235, 0.09344, 0.07961, 0.064, 0.0592, 0.10109, 0.19099, 0.21717, 0.68504, 0.98921, 1.00546, 1.03573, 1.04162, 1.07633, 1.11305, 0.99092, 0.68502, 0.48774, 0.31696, 0.26244, 0.24397, 0.18579, 0.06429, 0.01676, 0.00928, 0.02443, 0.07105, 0.09271, 0.36615, 0.5267, 0.77105, 1.0586, 1.07903, 0.97978, 0.88641, 0.4264, 0.75755, 1.04114, 1.05796, 1.08062, 1.04518, 0.84555, 0.3719, 0.03207, 0.04582, 0.08636, 0.07, 0.46024, 0.50652, 0.51189, 0.63852, 0.61066, 0.41029, 0.37907, 0.38753, 0.37945, 0.54222, 0.98941, 1.05398, 0.98093, 0.98198, 0.98255, 0.86059, 0.65766, 0.31689, 0.19072, 0.05827, 0.02405, 0.01934, 0.01586, 0.01798, 0.01928, 0.01623, 0.01477, 0.00987, 0.00764, 0.00692, 0.00669, 0.00353, 0.0035, 0.00185, 0.00153, 0.00136, 0.00114, 0.00093, 0.00076, 0.00049, 0.00049, 0.0003, 0.0004, 0.00026, 0.00018, 0.00109, 0.00549, 0.00861, 0.01638 ], "comparison": { "original": "लेकिन अगर इसे हम ध्यान से देखेंगे।", "retranscribed": "लेकिन अगर इसे हम ध्यान से देखेंगे", "reference_tokens": [ "लेकिन", "अगर", "इसे", "हम", "ध्यान", "से", "देखेंगे" ], "hypothesis_tokens": [ "लेकिन", "अगर", "इसे", "हम", "ध्यान", "से", "देखेंगे" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 7, "reference_words": 7, "hypothesis_words": 7, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "लेकिन", "hypothesis": "लेकिन", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "अगर", "hypothesis": "अगर", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "इसे", "hypothesis": "इसे", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "हम", "hypothesis": "हम", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "ध्यान", "hypothesis": "ध्यान", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "से", "hypothesis": "से", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "देखेंगे", "hypothesis": "देखेंगे", "reference_index": 6, "hypothesis_index": 6 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz float32 WAV", "source_peak_abs": 1.11305, "audio_sample_format": "float32" }, { "language": "Hindi", "emotion": "Disgusted", "emotion_confidence": 0.45019298791885376, "duration_seconds": 7.167000000000002, "mos": 3.1268, "audio_variant": "original", "original_transcript_raw": "इम्पॉसिबल मैं उसका टॉर्चर बर्दाश्त नहीं कर सकती। ही जस्ट डिस्कस्टिंग प्लीज मालिडी अपना हुस्सा ठंडा करो और थोड़ा कॉरपोरेट करो, प्लीज", "original_transcript": "इम्पॉसिबल मैं उसका टॉर्चर बर्दाश्त नहीं कर सकती। ही जस्ट डिस्कस्टिंग प्लीज मालिडी अपना हुस्सा ठंडा करो और थोड़ा कॉरपोरेट करो, प्लीज", "retranscribed_transcript": "इम्पॉसिबल मैं उसका टॉर्चर बर्दाश्त नहीं कर सकती ही इज जस्ट डिस्गस्टिंग प्लीज मालिक अपना गुस्सा ठंडा करो और थोड़ा कोपरेट करो प्लीज", "backend": "bodhan", "emotion_analyzed_seconds": 7.167, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-154", "energy": { "value": 0.76171875, "bucket": "high" }, "audio_url": "audio/utterance-154.wav", "spectrogram_url": "spectrograms/utterance-154.png", "waveform": [ 0.40829, 0.5316, 0.46214, 0.36482, 0.22747, 0.23057, 0.4155, 0.50777, 0.4531, 0.2634, 0.23605, 0.27766, 0.23225, 0.22671, 0.34631, 0.16088, 0.08834, 0.09664, 0.08011, 0.09723, 0.08634, 0.06301, 0.12484, 0.38913, 0.31843, 0.26903, 0.1927, 0.10055, 0.05684, 0.24016, 0.23231, 0.07523, 0.25795, 0.34453, 0.29052, 0.08526, 0.1579, 0.20123, 0.24485, 0.11457, 0.18324, 0.30032, 0.17956, 0.10433, 0.42803, 0.46472, 0.42408, 0.16695, 0.17037, 0.16669, 0.19028, 0.21451, 0.19452, 0.17338, 0.09605, 0.243, 0.17728, 0.1038, 0.07119, 0.16595, 0.11561, 0.03714, 0.04482, 0.16383, 0.16945, 0.09017, 0.06469, 0.03943, 0.04268, 0.03663, 0.04588, 0.25353, 0.22234, 0.17678, 0.11518, 0.15451, 0.34916, 0.27204, 0.16023, 0.04695, 0.06123, 0.38414, 0.39563, 0.22057, 0.09983, 0.05211, 0.31275, 0.45958, 0.40623, 0.13689, 0.05445, 0.0419, 0.14821, 0.33608, 0.31523, 0.22583, 0.15388, 0.05002, 0.21102, 0.42402, 0.38358, 0.32995, 0.2899, 0.11997, 0.05459, 0.12996, 0.14543, 0.09218, 0.07514, 0.09188, 0.03772, 0.06875, 0.0638, 0.04708, 0.02628, 0.03044, 0.03865, 0.03839, 0.29198, 0.21114, 0.0219, 0.24368, 0.52905, 0.37062, 0.11242, 0.22815, 0.34247, 0.14478, 0.14099, 0.47412, 0.38366, 0.14525, 0.08251, 0.10349, 0.25598, 0.24527, 0.27669, 0.31596, 0.24082, 0.05274, 0.18546, 0.23201, 0.29018, 0.29047, 0.3377, 0.332, 0.09151, 0.04401, 0.21509, 0.29864, 0.32406, 0.29817, 0.22491, 0.0368, 0.06746, 0.29471, 0.2484, 0.0806, 0.07393, 0.36929, 0.38261, 0.14298, 0.12188, 0.15972, 0.29567, 0.21323, 0.12091, 0.07982, 0.05703, 0.14081, 0.22491, 0.18144, 0.07342, 0.0457, 0.03497, 0.04317, 0.04307, 0.01772, 0.014, 0.00954 ], "comparison": { "original": "इम्पॉसिबल मैं उसका टॉर्चर बर्दाश्त नहीं कर सकती। ही जस्ट डिस्कस्टिंग प्लीज मालिडी अपना हुस्सा ठंडा करो और थोड़ा कॉरपोरेट करो, प्लीज", "retranscribed": "इम्पॉसिबल मैं उसका टॉर्चर बर्दाश्त नहीं कर सकती ही इज जस्ट डिस्गस्टिंग प्लीज मालिक अपना गुस्सा ठंडा करो और थोड़ा कोपरेट करो प्लीज", "reference_tokens": [ "इम्पॉसिबल", "मैं", "उसका", "टॉर्चर", "बर्दाश्त", "नहीं", "कर", "सकती", "ही", "जस्ट", "डिस्कस्टिंग", "प्लीज", "मालिडी", "अपना", "हुस्सा", "ठंडा", "करो", "और", "थोड़ा", "कॉरपोरेट", "करो", "प्लीज" ], "hypothesis_tokens": [ "इम्पॉसिबल", "मैं", "उसका", "टॉर्चर", "बर्दाश्त", "नहीं", "कर", "सकती", "ही", "इज", "जस्ट", "डिस्गस्टिंग", "प्लीज", "मालिक", "अपना", "गुस्सा", "ठंडा", "करो", "और", "थोड़ा", "कोपरेट", "करो", "प्लीज" ], "counts": { "substitutions": 4, "deletions": 0, "insertions": 1, "hits": 18, "reference_words": 22, "hypothesis_words": 23, "edits": 5 }, "wer": 0.22727272727272727, "wer_percent": 22.727272727272727, "alignment": [ { "op": "equal", "reference": "इम्पॉसिबल", "hypothesis": "इम्पॉसिबल", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "उसका", "hypothesis": "उसका", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "टॉर्चर", "hypothesis": "टॉर्चर", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "बर्दाश्त", "hypothesis": "बर्दाश्त", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "नहीं", "hypothesis": "नहीं", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "कर", "hypothesis": "कर", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "सकती", "hypothesis": "सकती", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "ही", "hypothesis": "ही", "reference_index": 8, "hypothesis_index": 8 }, { "op": "insert", "reference": null, "hypothesis": "इज", "reference_index": null, "hypothesis_index": 9 }, { "op": "equal", "reference": "जस्ट", "hypothesis": "जस्ट", "reference_index": 9, "hypothesis_index": 10 }, { "op": "substitute", "reference": "डिस्कस्टिंग", "hypothesis": "डिस्गस्टिंग", "reference_index": 10, "hypothesis_index": 11 }, { "op": "equal", "reference": "प्लीज", "hypothesis": "प्लीज", "reference_index": 11, "hypothesis_index": 12 }, { "op": "substitute", "reference": "मालिडी", "hypothesis": "मालिक", "reference_index": 12, "hypothesis_index": 13 }, { "op": "equal", "reference": "अपना", "hypothesis": "अपना", "reference_index": 13, "hypothesis_index": 14 }, { "op": "substitute", "reference": "हुस्सा", "hypothesis": "गुस्सा", "reference_index": 14, "hypothesis_index": 15 }, { "op": "equal", "reference": "ठंडा", "hypothesis": "ठंडा", "reference_index": 15, "hypothesis_index": 16 }, { "op": "equal", "reference": "करो", "hypothesis": "करो", "reference_index": 16, "hypothesis_index": 17 }, { "op": "equal", "reference": "और", "hypothesis": "और", "reference_index": 17, "hypothesis_index": 18 }, { "op": "equal", "reference": "थोड़ा", "hypothesis": "थोड़ा", "reference_index": 18, "hypothesis_index": 19 }, { "op": "substitute", "reference": "कॉरपोरेट", "hypothesis": "कोपरेट", "reference_index": 19, "hypothesis_index": 20 }, { "op": "equal", "reference": "करो", "hypothesis": "करो", "reference_index": 20, "hypothesis_index": 21 }, { "op": "equal", "reference": "प्लीज", "hypothesis": "प्लीज", "reference_index": 21, "hypothesis_index": 22 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.5316, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Disgusted", "emotion_confidence": 0.4236910343170166, "duration_seconds": 7.081999999999994, "mos": 3.2135, "audio_variant": "cleaned", "original_transcript_raw": "वेरी bad disgusting अरे भाभी जी भाभी जी नया डिजाइन है आप समझिए तो सही भाभी जी. ", "original_transcript": "वेरी bad disgusting अरे भाभी जी भाभी जी नया डिजाइन है आप समझिए तो सही भाभी जी.", "retranscribed_transcript": "वेरी बैड डिस्गस्टिंग अरे भाभी जी भाभी जी नया डिजाइन है आप समझिए तो सही भाभी जी", "backend": "bodhan", "emotion_analyzed_seconds": 7.082, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-155", "energy": { "value": 0.83984375, "bucket": "high" }, "audio_url": "audio/utterance-155.wav", "spectrogram_url": "spectrograms/utterance-155.png", "waveform": [ 0.42507, 0.46456, 0.27893, 0.24463, 0.37073, 0.28843, 0.2498, 0.43487, 0.36191, 0.2531, 0.1281, 0.0039, 0.0287, 0.03187, 0.10701, 0.08004, 0.32947, 0.35024, 0.21241, 0.05771, 0.04993, 0.38151, 0.43876, 0.37394, 0.06603, 0.02112, 0.01113, 0.09453, 0.117, 0.10091, 0.02162, 0.00233, 0.00031, 0.21852, 0.37663, 0.31183, 0.16179, 0.06653, 0.37175, 0.53841, 0.41048, 0.0318, 0.44599, 0.33525, 0.25763, 0.08265, 0.11966, 0.05782, 0.29833, 0.21853, 0.27592, 0.25087, 0.04719, 0.00062, 0.00308, 0.00527, 0.00394, 0.00084, 0.00012, 9e-05, 0.00011, 0.1803, 0.18735, 0.05806, 0.02489, 0.44316, 0.39307, 0.17648, 0.01014, 0.41955, 0.28615, 0.12378, 0.20455, 0.31221, 0.29803, 0.21808, 0.25765, 0.54115, 0.46786, 0.37827, 0.12453, 0.15269, 0.56178, 0.49483, 0.41125, 0.13991, 0.54315, 0.54528, 0.56395, 0.39898, 0.14806, 0.55116, 0.53288, 0.54058, 0.54821, 0.48733, 0.56832, 0.54332, 0.33152, 0.27977, 0.02982, 0.11466, 0.12376, 0.07897, 0.03358, 0.50836, 0.44965, 0.23975, 0.04127, 0.02595, 0.49172, 0.42698, 0.07192, 0.11914, 0.536, 0.36021, 0.21152, 0.58848, 0.51423, 0.49833, 0.30042, 0.24196, 0.45868, 0.45198, 0.41868, 0.55596, 0.50106, 0.50711, 0.33787, 0.00722, 0.06366, 0.30083, 0.30594, 0.0222, 0.05457, 0.13511, 0.23522, 0.16236, 0.05593, 0.05222, 0.41254, 0.50867, 0.59697, 0.36601, 0.42506, 0.49903, 0.25903, 0.49234, 0.57959, 0.1236, 0.46075, 0.58101, 0.3743, 0.38619, 0.14025, 0.00084, 0.00255, 0.00497, 0.00689, 0.00707, 0.00601, 0.00437, 0.00268, 0.00202, 0.00044, 0.00013, 0.0032, 0.56267, 0.4083, 0.59356, 0.49317, 0.32024, 0.21779, 0.54363, 0.39324, 0.3796, 0.22795, 0.02338, 0.00073, 0.00256 ], "comparison": { "original": "वेरी bad disgusting अरे भाभी जी भाभी जी नया डिजाइन है आप समझिए तो सही भाभी जी.", "retranscribed": "वेरी बैड डिस्गस्टिंग अरे भाभी जी भाभी जी नया डिजाइन है आप समझिए तो सही भाभी जी", "reference_tokens": [ "वेरी", "bad", "disgusting", "अरे", "भाभी", "जी", "भाभी", "जी", "नया", "डिजाइन", "है", "आप", "समझिए", "तो", "सही", "भाभी", "जी" ], "hypothesis_tokens": [ "वेरी", "बैड", "डिस्गस्टिंग", "अरे", "भाभी", "जी", "भाभी", "जी", "नया", "डिजाइन", "है", "आप", "समझिए", "तो", "सही", "भाभी", "जी" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 15, "reference_words": 17, "hypothesis_words": 17, "edits": 2 }, "wer": 0.11764705882352941, "wer_percent": 11.76470588235294, "alignment": [ { "op": "equal", "reference": "वेरी", "hypothesis": "वेरी", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "bad", "hypothesis": "बैड", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "disgusting", "hypothesis": "डिस्गस्टिंग", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "अरे", "hypothesis": "अरे", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "भाभी", "hypothesis": "भाभी", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "जी", "hypothesis": "जी", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "भाभी", "hypothesis": "भाभी", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "जी", "hypothesis": "जी", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "नया", "hypothesis": "नया", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "डिजाइन", "hypothesis": "डिजाइन", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "आप", "hypothesis": "आप", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "समझिए", "hypothesis": "समझिए", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "तो", "hypothesis": "तो", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "सही", "hypothesis": "सही", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "भाभी", "hypothesis": "भाभी", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "जी", "hypothesis": "जी", "reference_index": 16, "hypothesis_index": 16 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.59697, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Fearful", "emotion_confidence": 0.2988739609718323, "duration_seconds": 2.031000000000006, "mos": 2.9751, "audio_variant": "cleaned", "original_transcript_raw": "मेरे घर पर पुलिस की रेड पड़ी है। ", "original_transcript": "मेरे घर पर पुलिस की रेड पड़ी है।", "retranscribed_transcript": "मेरे घर पर पुलिस की रेड पड़ी है", "backend": "bodhan", "emotion_analyzed_seconds": 2.031, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-156", "energy": { "value": 0.57421875, "bucket": "medium" }, "audio_url": "audio/utterance-156.wav", "spectrogram_url": "spectrograms/utterance-156.png", "waveform": [ 0.01356, 0.02902, 0.05204, 0.08713, 0.11351, 0.14101, 0.158, 0.15168, 0.1537, 0.16037, 0.17684, 0.18, 0.17396, 0.17081, 0.16201, 0.17022, 0.1657, 0.15792, 0.1578, 0.15367, 0.16612, 0.17489, 0.20851, 0.22161, 0.21644, 0.17896, 0.17461, 0.15547, 0.15953, 0.15753, 0.16048, 0.188, 0.19764, 0.19885, 0.21813, 0.28286, 0.32349, 0.36968, 0.37025, 0.46615, 0.62819, 0.62403, 0.58886, 0.55112, 0.52489, 0.47523, 0.27299, 0.42149, 0.49472, 0.47608, 0.45898, 0.39696, 0.32613, 0.22602, 0.22058, 0.24388, 0.32652, 0.37888, 0.4808, 0.4785, 0.49108, 0.43579, 0.46724, 0.40498, 0.19067, 0.27135, 0.22204, 0.12419, 0.04791, 0.02113, 0.00521, 0.00726, 0.03758, 0.52625, 0.55375, 0.51916, 0.32144, 0.25878, 0.32674, 0.2527, 0.09757, 0.04535, 0.01725, 0.00687, 0.0075, 0.0061, 0.04569, 0.40152, 0.41643, 0.373, 0.35266, 0.35253, 0.32741, 0.31315, 0.3317, 0.38917, 0.41984, 0.48303, 0.46493, 0.42147, 0.29966, 0.23183, 0.15348, 0.07699, 0.0625, 0.03974, 0.00985, 0.00745, 0.00698, 0.06274, 0.09783, 0.28302, 0.45782, 0.5005, 0.43513, 0.4323, 0.36015, 0.23412, 0.1936, 0.27267, 0.42083, 0.47306, 0.46912, 0.58203, 0.61374, 0.54087, 0.49733, 0.49535, 0.46831, 0.4136, 0.30312, 0.15198, 0.10476, 0.17779, 0.15923, 0.08898, 0.04049, 0.01226, 0.00566, 0.0065, 0.00642, 0.01367, 0.51599, 0.58426, 0.45219, 0.4218, 0.44729, 0.39516, 0.24453, 0.11462, 0.11754, 0.15073, 0.29479, 0.28973, 0.28715, 0.24789, 0.26216, 0.27979, 0.29057, 0.3039, 0.3114, 0.28321, 0.23977, 0.187, 0.18016, 0.23078, 0.20584, 0.23834, 0.18504, 0.13593, 0.11218, 0.07191, 0.07519, 0.06282, 0.03845, 0.01854, 0.01688, 0.01407, 0.0106, 0.01384 ], "comparison": { "original": "मेरे घर पर पुलिस की रेड पड़ी है।", "retranscribed": "मेरे घर पर पुलिस की रेड पड़ी है", "reference_tokens": [ "मेरे", "घर", "पर", "पुलिस", "की", "रेड", "पड़ी", "है" ], "hypothesis_tokens": [ "मेरे", "घर", "पर", "पुलिस", "की", "रेड", "पड़ी", "है" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 8, "reference_words": 8, "hypothesis_words": 8, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "मेरे", "hypothesis": "मेरे", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "घर", "hypothesis": "घर", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "पर", "hypothesis": "पर", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "पुलिस", "hypothesis": "पुलिस", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "की", "hypothesis": "की", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "रेड", "hypothesis": "रेड", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "पड़ी", "hypothesis": "पड़ी", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 7, "hypothesis_index": 7 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.62819, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Fearful", "emotion_confidence": 0.3179607093334198, "duration_seconds": 1.9279999999999973, "mos": 2.8281, "audio_variant": "cleaned", "original_transcript_raw": "وردها شرم كهال", "original_transcript": "وردها شرم كهال", "retranscribed_transcript": "वृद्धाश्रम कहाँ है", "backend": "bodhan", "emotion_analyzed_seconds": 1.928, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-157", "energy": { "value": 0.52734375, "bucket": "medium" }, "audio_url": "audio/utterance-157.wav", "spectrogram_url": "spectrograms/utterance-157.png", "waveform": [ 0.16206, 0.16911, 0.06431, 0.0577, 0.02593, 0.00242, 0.014, 0.03037, 0.04945, 0.05949, 0.04429, 0.06382, 0.07689, 0.05719, 0.06938, 0.07681, 0.10497, 0.13435, 0.14919, 0.18584, 0.23434, 0.29662, 0.40614, 0.54394, 0.51388, 0.6906, 0.71012, 0.76647, 0.74052, 0.68218, 0.61958, 0.51399, 0.32492, 0.39506, 0.06969, 0.12937, 0.11854, 0.08205, 0.05289, 0.01646, 0.00353, 0.0007, 0.00084, 0.00081, 0.00149, 0.04765, 0.42578, 0.45092, 0.44471, 0.43208, 0.40962, 0.35693, 0.30329, 0.2949, 0.29824, 0.32756, 0.34637, 0.39601, 0.4227, 0.46489, 0.60743, 0.65289, 0.99986, 0.9991, 1.03347, 1.04493, 1.04388, 0.634, 0.6403, 1.0072, 1.02868, 1.04437, 1.02658, 1.0478, 1.02677, 1.02613, 0.43788, 0.28798, 0.18009, 0.10796, 0.04802, 0.01003, 0.00967, 0.23833, 0.58322, 0.45953, 0.44014, 0.43702, 0.71144, 0.59182, 0.79374, 1.07256, 0.99788, 0.99098, 0.99913, 0.9877, 0.93505, 0.65885, 0.62157, 0.82269, 0.74125, 0.52998, 0.61561, 0.78872, 0.71098, 0.44253, 0.36111, 0.24581, 0.13765, 0.44024, 0.97178, 0.8542, 0.72844, 0.81696, 1.0164, 1.037, 1.03049, 1.0536, 1.04277, 0.9567, 0.9256, 0.92862, 0.89592, 0.80254, 0.53176, 0.26467, 0.04436, 0.02771, 0.00375, 0.00313, 0.44708, 0.23966, 0.79177, 0.26818, 1.06609, 1.09083, 1.05316, 1.01553, 0.81462, 0.75698, 0.93813, 0.70671, 0.29936, 0.29615, 0.28841, 0.34966, 0.36592, 0.25824, 0.32734, 0.32295, 0.35659, 0.99658, 1.03205, 1.01967, 0.99314, 1.02724, 0.92549, 0.91712, 0.86023, 0.78959, 0.69011, 0.63659, 0.5428, 0.41789, 0.2725, 0.0957, 0.00826, 0.00166, 0.00061, 0.00049, 0.00044, 0.00037, 0.00034, 0.00032, 0.00025, 0.00546, 0.04452, 0.05968, 0.07317, 0.0923 ], "comparison": { "original": "وردها شرم كهال", "retranscribed": "वृद्धाश्रम कहाँ है", "reference_tokens": [ "وردها", "شرم", "كهال" ], "hypothesis_tokens": [ "वृद्धाश्रम", "कहाँ", "है" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 0, "hits": 0, "reference_words": 3, "hypothesis_words": 3, "edits": 3 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "substitute", "reference": "وردها", "hypothesis": "वृद्धाश्रम", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "شرم", "hypothesis": "कहाँ", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "كهال", "hypothesis": "है", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz float32 WAV", "source_peak_abs": 1.09083, "audio_sample_format": "float32" }, { "language": "Hindi", "emotion": "Fearful", "emotion_confidence": 0.6141811609268188, "duration_seconds": 7.167000000000002, "mos": 2.9402, "audio_variant": "cleaned", "original_transcript_raw": "इतना गुस्सा काय कर रहे हैं, मिस्टर जी कुछ होने की है। ", "original_transcript": "इतना गुस्सा काय कर रहे हैं, मिस्टर जी कुछ होने की है।", "retranscribed_transcript": "हम बाबू जी अम्मा जी इतना गुस्सा काहे कर रहे हैं मिस्टर जी कुछ नहीं किए", "backend": "bodhan", "emotion_analyzed_seconds": 7.167, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-158", "energy": { "value": 0.55859375, "bucket": "medium" }, "audio_url": "audio/utterance-158.wav", "spectrogram_url": "spectrograms/utterance-158.png", "waveform": [ 0.17797, 0.0468, 0.00797, 0.03041, 0.05667, 0.07842, 0.07857, 0.2619, 0.40951, 0.16727, 0.14004, 0.1386, 0.13177, 0.0948, 0.07667, 0.03394, 0.02496, 0.01167, 0.00818, 0.00595, 0.0044, 0.00375, 0.00212, 0.00239, 0.00182, 0.00182, 0.00158, 0.00145, 0.00153, 0.00115, 0.00122, 0.02407, 0.10925, 0.10236, 0.09728, 0.3167, 0.10353, 0.01461, 0.08137, 0.13063, 0.65761, 0.33678, 0.36488, 0.06411, 0.2653, 0.24366, 0.16612, 0.10723, 0.26915, 0.25811, 0.19486, 0.14192, 0.063, 0.00208, 0.00155, 0.24409, 0.30106, 0.12682, 0.00579, 0.04291, 0.11787, 0.23005, 0.16842, 0.21696, 0.29373, 0.30018, 0.25809, 0.1534, 0.10071, 0.14692, 0.19277, 0.09167, 0.00739, 0.02017, 0.03009, 0.03742, 0.02572, 0.01049, 0.12167, 0.17587, 0.13793, 0.07763, 0.06375, 0.02428, 0.00085, 0.00089, 0.00087, 0.00116, 0.02669, 0.08879, 0.12111, 0.0455, 0.00828, 0.00085, 0.00077, 0.00069, 0.00077, 0.00125, 0.07263, 0.08418, 0.20292, 0.19847, 0.19023, 0.13177, 0.19843, 0.20279, 0.01485, 0.00797, 0.32652, 0.50568, 0.4536, 0.10867, 0.21155, 0.27158, 0.03836, 0.0471, 0.25008, 0.40007, 0.37145, 0.00467, 0.40441, 0.33008, 0.37056, 0.48578, 0.2502, 0.02777, 0.10146, 0.24259, 0.19476, 0.19546, 0.14652, 0.24006, 0.22665, 0.3168, 0.3, 0.1706, 0.01532, 0.02615, 0.03957, 0.04771, 0.04694, 0.00233, 0.00134, 0.00157, 0.00175, 0.01867, 0.19952, 0.27962, 0.35035, 0.14618, 0.02988, 0.33746, 0.3631, 0.14539, 0.38834, 0.41595, 0.04635, 0.31613, 0.31775, 0.06414, 0.12646, 0.19876, 0.30281, 0.26218, 0.36517, 0.36583, 0.34008, 0.32365, 0.04778, 0.0339, 0.19021, 0.18673, 0.16432, 0.15424, 0.07232, 0.03476, 0.0212, 0.00695, 0.01368, 0.06961 ], "comparison": { "original": "इतना गुस्सा काय कर रहे हैं, मिस्टर जी कुछ होने की है।", "retranscribed": "हम बाबू जी अम्मा जी इतना गुस्सा काहे कर रहे हैं मिस्टर जी कुछ नहीं किए", "reference_tokens": [ "इतना", "गुस्सा", "काय", "कर", "रहे", "हैं", "मिस्टर", "जी", "कुछ", "होने", "की", "है" ], "hypothesis_tokens": [ "हम", "बाबू", "जी", "अम्मा", "जी", "इतना", "गुस्सा", "काहे", "कर", "रहे", "हैं", "मिस्टर", "जी", "कुछ", "नहीं", "किए" ], "counts": { "substitutions": 3, "deletions": 1, "insertions": 5, "hits": 8, "reference_words": 12, "hypothesis_words": 16, "edits": 9 }, "wer": 0.75, "wer_percent": 75.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "हम", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "बाबू", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "जी", "reference_index": null, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "अम्मा", "reference_index": null, "hypothesis_index": 3 }, { "op": "insert", "reference": null, "hypothesis": "जी", "reference_index": null, "hypothesis_index": 4 }, { "op": "equal", "reference": "इतना", "hypothesis": "इतना", "reference_index": 0, "hypothesis_index": 5 }, { "op": "equal", "reference": "गुस्सा", "hypothesis": "गुस्सा", "reference_index": 1, "hypothesis_index": 6 }, { "op": "substitute", "reference": "काय", "hypothesis": "काहे", "reference_index": 2, "hypothesis_index": 7 }, { "op": "equal", "reference": "कर", "hypothesis": "कर", "reference_index": 3, "hypothesis_index": 8 }, { "op": "equal", "reference": "रहे", "hypothesis": "रहे", "reference_index": 4, "hypothesis_index": 9 }, { "op": "equal", "reference": "हैं", "hypothesis": "हैं", "reference_index": 5, "hypothesis_index": 10 }, { "op": "equal", "reference": "मिस्टर", "hypothesis": "मिस्टर", "reference_index": 6, "hypothesis_index": 11 }, { "op": "equal", "reference": "जी", "hypothesis": "जी", "reference_index": 7, "hypothesis_index": 12 }, { "op": "equal", "reference": "कुछ", "hypothesis": "कुछ", "reference_index": 8, "hypothesis_index": 13 }, { "op": "delete", "reference": "होने", "hypothesis": null, "reference_index": 9, "hypothesis_index": null }, { "op": "substitute", "reference": "की", "hypothesis": "नहीं", "reference_index": 10, "hypothesis_index": 14 }, { "op": "substitute", "reference": "है", "hypothesis": "किए", "reference_index": 11, "hypothesis_index": 15 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.65761, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Fearful", "emotion_confidence": 0.5153058767318726, "duration_seconds": 9.991, "mos": 3.2422, "audio_variant": "cleaned", "original_transcript_raw": "प्लीज मेरी बात सुनिए सर मैडम मैडम, चलिए आप यहाँ से चलिए जाइए यहाँ से मैडम, आप प्लीज मेरी बात सैडम", "original_transcript": "प्लीज मेरी बात सुनिए सर मैडम मैडम, चलिए आप यहाँ से चलिए जाइए यहाँ से मैडम, आप प्लीज मेरी बात सैडम", "retranscribed_transcript": "प्लीज़ मेरी बात सुनिए सर मैडम मैडम चलिए आप यहाँ से आप चलिए जाइए यहाँ से मैडम आप प्लीज़ मेरी बात प्लीज़ मैडम सर सर प्लीज़", "backend": "bodhan", "emotion_analyzed_seconds": 9.991, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-159", "energy": { "value": 0.72265625, "bucket": "high" }, "audio_url": "audio/utterance-159.wav", "spectrogram_url": "spectrograms/utterance-159.png", "waveform": [ 0.00249, 0.00673, 0.00223, 0.00155, 0.00211, 0.00282, 0.00355, 0.00384, 0.00346, 0.00213, 0.00171, 0.00096, 0.00073, 0.00139, 0.00146, 0.00163, 0.00128, 0.00249, 0.00313, 0.00577, 0.07403, 0.12863, 0.09005, 0.02169, 0.10231, 0.10011, 0.07264, 0.15968, 0.19066, 0.2317, 0.01049, 0.06683, 0.06251, 0.10267, 0.11375, 0.05556, 0.05869, 0.03668, 0.00657, 0.00286, 0.00062, 0.00025, 0.00012, 0.00021, 0.01846, 0.32529, 0.36264, 0.3779, 0.2097, 0.03575, 0.01127, 0.01196, 0.01074, 0.00676, 0.0093, 0.10194, 0.07814, 0.0952, 0.04107, 0.0427, 0.05529, 0.01793, 0.01513, 0.01623, 0.00954, 0.00337, 0.00196, 0.00151, 0.10071, 0.39818, 0.39999, 0.32904, 0.17397, 0.09273, 0.33194, 0.25584, 0.5422, 0.4939, 0.45189, 0.31392, 0.29, 0.33518, 0.21592, 0.27043, 0.10206, 0.00131, 0.00045, 0.00036, 0.00681, 0.10269, 0.00873, 0.06893, 0.19988, 0.23181, 0.11817, 0.30557, 0.40866, 0.27463, 0.35441, 0.11993, 0.5338, 0.64924, 0.44745, 0.43907, 0.48152, 0.4824, 0.38977, 0.3203, 0.33729, 0.29931, 0.33402, 0.27678, 0.2751, 0.09201, 0.00293, 0.00186, 0.00065, 0.00043, 0.00328, 0.00662, 0.05188, 0.05584, 0.05353, 0.00846, 0.12458, 0.09327, 0.04611, 0.16685, 0.29832, 0.17719, 0.23318, 0.37544, 0.41251, 0.18908, 0.02447, 0.03809, 0.04231, 0.01961, 0.07759, 0.11497, 0.15993, 0.10643, 0.06265, 0.01121, 0.0013, 0.00076, 0.00018, 0.00022, 0.00103, 0.00193, 0.00346, 0.0033, 0.00622, 0.00715, 0.16775, 0.16518, 0.192, 0.09804, 0.05617, 0.01419, 0.00293, 0.00186, 0.00447, 0.00689, 0.11397, 0.10759, 0.01812, 0.01924, 0.04516, 0.05433, 0.05754, 0.00625, 0.00334, 0.00026, 4e-05, 2e-05, 2e-05, 2e-05, 2e-05, 0.09368 ], "comparison": { "original": "प्लीज मेरी बात सुनिए सर मैडम मैडम, चलिए आप यहाँ से चलिए जाइए यहाँ से मैडम, आप प्लीज मेरी बात सैडम", "retranscribed": "प्लीज़ मेरी बात सुनिए सर मैडम मैडम चलिए आप यहाँ से आप चलिए जाइए यहाँ से मैडम आप प्लीज़ मेरी बात प्लीज़ मैडम सर सर प्लीज़", "reference_tokens": [ "प्लीज", "मेरी", "बात", "सुनिए", "सर", "मैडम", "मैडम", "चलिए", "आप", "यहाँ", "से", "चलिए", "जाइए", "यहाँ", "से", "मैडम", "आप", "प्लीज", "मेरी", "बात", "सैडम" ], "hypothesis_tokens": [ "प्लीज़", "मेरी", "बात", "सुनिए", "सर", "मैडम", "मैडम", "चलिए", "आप", "यहाँ", "से", "आप", "चलिए", "जाइए", "यहाँ", "से", "मैडम", "आप", "प्लीज़", "मेरी", "बात", "प्लीज़", "मैडम", "सर", "सर", "प्लीज़" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 5, "hits": 18, "reference_words": 21, "hypothesis_words": 26, "edits": 8 }, "wer": 0.38095238095238093, "wer_percent": 38.095238095238095, "alignment": [ { "op": "substitute", "reference": "प्लीज", "hypothesis": "प्लीज़", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "मेरी", "hypothesis": "मेरी", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "बात", "hypothesis": "बात", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "सुनिए", "hypothesis": "सुनिए", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "सर", "hypothesis": "सर", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "मैडम", "hypothesis": "मैडम", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "मैडम", "hypothesis": "मैडम", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "चलिए", "hypothesis": "चलिए", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "आप", "hypothesis": "आप", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "यहाँ", "hypothesis": "यहाँ", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "से", "hypothesis": "से", "reference_index": 10, "hypothesis_index": 10 }, { "op": "insert", "reference": null, "hypothesis": "आप", "reference_index": null, "hypothesis_index": 11 }, { "op": "equal", "reference": "चलिए", "hypothesis": "चलिए", "reference_index": 11, "hypothesis_index": 12 }, { "op": "equal", "reference": "जाइए", "hypothesis": "जाइए", "reference_index": 12, "hypothesis_index": 13 }, { "op": "equal", "reference": "यहाँ", "hypothesis": "यहाँ", "reference_index": 13, "hypothesis_index": 14 }, { "op": "equal", "reference": "से", "hypothesis": "से", "reference_index": 14, "hypothesis_index": 15 }, { "op": "equal", "reference": "मैडम", "hypothesis": "मैडम", "reference_index": 15, "hypothesis_index": 16 }, { "op": "equal", "reference": "आप", "hypothesis": "आप", "reference_index": 16, "hypothesis_index": 17 }, { "op": "substitute", "reference": "प्लीज", "hypothesis": "प्लीज़", "reference_index": 17, "hypothesis_index": 18 }, { "op": "equal", "reference": "मेरी", "hypothesis": "मेरी", "reference_index": 18, "hypothesis_index": 19 }, { "op": "equal", "reference": "बात", "hypothesis": "बात", "reference_index": 19, "hypothesis_index": 20 }, { "op": "insert", "reference": null, "hypothesis": "प्लीज़", "reference_index": null, "hypothesis_index": 21 }, { "op": "insert", "reference": null, "hypothesis": "मैडम", "reference_index": null, "hypothesis_index": 22 }, { "op": "insert", "reference": null, "hypothesis": "सर", "reference_index": null, "hypothesis_index": 23 }, { "op": "insert", "reference": null, "hypothesis": "सर", "reference_index": null, "hypothesis_index": 24 }, { "op": "substitute", "reference": "सैडम", "hypothesis": "प्लीज़", "reference_index": 20, "hypothesis_index": 25 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.64924, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Fearful", "emotion_confidence": 0.40058663487434387, "duration_seconds": 1.6210000000000093, "mos": 3.1793, "audio_variant": "cleaned", "original_transcript_raw": "な お 店 を デ ィ シ ョ ン で ク ロ シ", "original_transcript": "な お 店 を デ ィ シ ョ ン で ク ロ シ", "retranscribed_transcript": "राम इज़ अदिशुंदे क्रॉस", "backend": "bodhan", "emotion_analyzed_seconds": 1.621, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-160", "energy": { "value": 0.81640625, "bucket": "high" }, "audio_url": "audio/utterance-160.wav", "spectrogram_url": "spectrograms/utterance-160.png", "waveform": [ 0.05622, 0.04693, 0.03912, 0.17298, 0.34148, 0.28474, 0.20823, 0.22159, 0.23863, 0.15117, 0.2087, 0.19923, 0.22823, 0.2152, 0.20933, 0.21991, 0.20666, 0.3392, 0.36171, 0.37652, 0.38679, 0.28406, 0.16265, 0.16413, 0.15953, 0.14524, 0.12464, 0.21354, 0.17577, 0.18743, 0.20304, 0.21547, 0.19101, 0.12982, 0.06126, 0.06696, 0.07002, 0.06807, 0.05054, 0.11543, 0.3822, 0.43622, 0.32289, 0.26125, 0.29951, 0.25205, 0.24702, 0.22203, 0.2465, 0.246, 0.21499, 0.17643, 0.14444, 0.18093, 0.19378, 0.05518, 0.01616, 0.01399, 0.04127, 0.05063, 0.18761, 0.29145, 0.3116, 0.3013, 0.22622, 0.14379, 0.11544, 0.14788, 0.1322, 0.1406, 0.13378, 0.14163, 0.14671, 0.10335, 0.08357, 0.11147, 0.15017, 0.16016, 0.1469, 0.12819, 0.13651, 0.05366, 0.0297, 0.02656, 0.02336, 0.02724, 0.03553, 0.04028, 0.04351, 0.04867, 0.06817, 0.23882, 0.30889, 0.32457, 0.30123, 0.2481, 0.18875, 0.19548, 0.19412, 0.11347, 0.02786, 0.01401, 0.00472, 0.00151, 0.00082, 0.00067, 0.05918, 0.08234, 0.10128, 0.06229, 0.16385, 0.18963, 0.21669, 0.17466, 0.15083, 0.13022, 0.16875, 0.20169, 0.17825, 0.18193, 0.14897, 0.14062, 0.15989, 0.13658, 0.15074, 0.14726, 0.17334, 0.18865, 0.20656, 0.24393, 0.35095, 0.3004, 0.28963, 0.30143, 0.30628, 0.30002, 0.23543, 0.25764, 0.26213, 0.28734, 0.15551, 0.19236, 0.18796, 0.14964, 0.10749, 0.09781, 0.08607, 0.04946, 0.05235, 0.05909, 0.04447, 0.04251, 0.03459, 0.05175, 0.05538, 0.09476, 0.08477, 0.09756, 0.08968, 0.08404, 0.0861, 0.07567, 0.08404, 0.04229, 0.04442, 0.04274, 0.04049, 0.02658, 0.02171, 0.01565, 0.0128, 0.00619, 0.0036, 0.00118, 0.00231, 0.00779, 0.01195, 0.0202, 0.02434, 0.02061 ], "comparison": { "original": "な お 店 を デ ィ シ ョ ン で ク ロ シ", "retranscribed": "राम इज़ अदिशुंदे क्रॉस", "reference_tokens": [ "な", "お", "店", "を", "デ", "ィ", "シ", "ョ", "ン", "で", "ク", "ロ", "シ" ], "hypothesis_tokens": [ "राम", "इज़", "अदिशुंदे", "क्रॉस" ], "counts": { "substitutions": 4, "deletions": 9, "insertions": 0, "hits": 0, "reference_words": 13, "hypothesis_words": 4, "edits": 13 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "delete", "reference": "な", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "delete", "reference": "お", "hypothesis": null, "reference_index": 1, "hypothesis_index": null }, { "op": "delete", "reference": "店", "hypothesis": null, "reference_index": 2, "hypothesis_index": null }, { "op": "delete", "reference": "を", "hypothesis": null, "reference_index": 3, "hypothesis_index": null }, { "op": "delete", "reference": "デ", "hypothesis": null, "reference_index": 4, "hypothesis_index": null }, { "op": "delete", "reference": "ィ", "hypothesis": null, "reference_index": 5, "hypothesis_index": null }, { "op": "delete", "reference": "シ", "hypothesis": null, "reference_index": 6, "hypothesis_index": null }, { "op": "delete", "reference": "ョ", "hypothesis": null, "reference_index": 7, "hypothesis_index": null }, { "op": "delete", "reference": "ン", "hypothesis": null, "reference_index": 8, "hypothesis_index": null }, { "op": "substitute", "reference": "で", "hypothesis": "राम", "reference_index": 9, "hypothesis_index": 0 }, { "op": "substitute", "reference": "ク", "hypothesis": "इज़", "reference_index": 10, "hypothesis_index": 1 }, { "op": "substitute", "reference": "ロ", "hypothesis": "अदिशुंदे", "reference_index": 11, "hypothesis_index": 2 }, { "op": "substitute", "reference": "シ", "hypothesis": "क्रॉस", "reference_index": 12, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.43622, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Fearful", "emotion_confidence": 0.31244921684265137, "duration_seconds": 2.3700000000000045, "mos": 2.8106, "audio_variant": "cleaned", "original_transcript_raw": "Parirò. ", "original_transcript": "Parirò.", "retranscribed_transcript": "चलो ठीक है जाओ किचन में बनो सुपर हीरो", "backend": "bodhan", "emotion_analyzed_seconds": 2.37, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-161", "energy": { "value": 0.62109375, "bucket": "high" }, "audio_url": "audio/utterance-161.wav", "spectrogram_url": "spectrograms/utterance-161.png", "waveform": [ 0.16796, 0.4858, 0.49864, 0.43607, 0.17492, 0.10697, 0.07198, 0.20928, 0.26107, 0.31931, 0.24308, 0.17626, 0.03147, 0.00776, 0.00081, 0.00051, 0.10019, 0.10962, 0.07395, 0.06163, 0.09408, 0.14514, 0.09839, 0.05678, 0.00686, 0.00047, 0.00026, 0.00456, 0.19038, 0.10834, 0.42611, 0.38511, 0.29253, 0.08362, 0.02169, 0.10114, 0.16094, 0.28505, 0.23303, 0.54119, 0.68188, 0.49688, 0.64456, 0.67055, 0.39329, 0.31171, 0.30423, 0.41883, 0.39107, 0.46049, 0.34821, 0.27287, 0.28563, 0.23876, 0.22277, 0.2003, 0.25542, 0.19812, 0.15547, 0.19528, 0.07592, 0.07907, 0.08338, 0.06397, 0.06765, 0.06766, 0.04557, 0.04184, 0.01878, 0.01506, 0.01102, 0.00579, 0.00161, 0.00049, 0.00033, 0.00024, 0.0002, 0.00018, 0.00107, 0.14385, 0.11283, 0.64012, 0.60115, 0.48812, 0.12106, 0.01354, 0.04336, 0.15865, 0.25584, 0.25641, 0.23789, 0.27645, 0.4668, 0.43828, 0.23947, 0.16347, 0.30487, 0.37964, 0.37802, 0.37613, 0.38081, 0.39172, 0.76346, 0.71483, 0.6801, 0.19555, 0.08281, 0.10666, 0.4233, 0.66626, 0.78861, 0.67343, 0.62746, 0.53394, 0.36538, 0.22097, 0.25163, 0.47724, 0.46312, 0.48684, 0.50465, 0.50145, 0.44546, 0.28852, 0.14874, 0.11163, 0.08542, 0.06549, 0.08952, 0.09362, 0.07779, 0.48729, 0.57535, 0.46154, 0.34105, 0.09733, 0.05111, 0.00629, 0.00191, 0.00038, 0.00136, 0.24236, 0.56892, 0.48379, 0.34562, 0.33057, 0.1864, 0.1665, 0.15897, 0.17439, 0.17018, 0.13541, 0.08117, 0.0523, 0.09039, 0.21251, 0.25395, 0.39167, 0.4155, 0.27535, 0.3636, 0.55049, 0.64643, 0.62766, 0.5962, 0.49958, 0.43608, 0.42556, 0.40758, 0.36478, 0.23827, 0.17393, 0.07371, 0.0786, 0.05961, 0.0468, 0.0177, 0.00239, 0.00072, 0.00032 ], "comparison": { "original": "Parirò.", "retranscribed": "चलो ठीक है जाओ किचन में बनो सुपर हीरो", "reference_tokens": [ "parirò" ], "hypothesis_tokens": [ "चलो", "ठीक", "है", "जाओ", "किचन", "में", "बनो", "सुपर", "हीरो" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 8, "hits": 0, "reference_words": 1, "hypothesis_words": 9, "edits": 9 }, "wer": 9.0, "wer_percent": 900.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "चलो", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "ठीक", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "है", "reference_index": null, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "जाओ", "reference_index": null, "hypothesis_index": 3 }, { "op": "insert", "reference": null, "hypothesis": "किचन", "reference_index": null, "hypothesis_index": 4 }, { "op": "insert", "reference": null, "hypothesis": "में", "reference_index": null, "hypothesis_index": 5 }, { "op": "insert", "reference": null, "hypothesis": "बनो", "reference_index": null, "hypothesis_index": 6 }, { "op": "insert", "reference": null, "hypothesis": "सुपर", "reference_index": null, "hypothesis_index": 7 }, { "op": "substitute", "reference": "parirò", "hypothesis": "हीरो", "reference_index": 0, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.78861, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Happy", "emotion_confidence": 0.5678755640983582, "duration_seconds": 5.016999999999996, "mos": 2.9343, "audio_variant": "cleaned", "original_transcript_raw": "Que ambuل", "original_transcript": "Que ambuل", "retranscribed_transcript": "क्यों हम टुकड़ों में जिए", "backend": "bodhan", "emotion_analyzed_seconds": 5.017, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-162", "energy": { "value": 0.46484375, "bucket": "low" }, "audio_url": "audio/utterance-162.wav", "spectrogram_url": "spectrograms/utterance-162.png", "waveform": [ 0.066, 0.02646, 0.00071, 0.00055, 0.00043, 0.00032, 0.0002, 7e-05, 4e-05, 3e-05, 6e-05, 0.04148, 0.01108, 0.03721, 0.12136, 0.15006, 0.15216, 0.13875, 0.09776, 0.13489, 0.15104, 0.14968, 0.07048, 0.04971, 0.10904, 0.18407, 0.21638, 0.18749, 0.11757, 0.06287, 0.08566, 0.08612, 0.0818, 0.05468, 0.04641, 0.0524, 0.06019, 0.0508, 0.04913, 0.02965, 0.01402, 0.00322, 0.01749, 0.04022, 0.05198, 0.05492, 0.04673, 0.04492, 0.03611, 0.01431, 0.00042, 0.00012, 0.00178, 0.07328, 0.19411, 0.16667, 0.1521, 0.13432, 0.11335, 0.03996, 0.00254, 0.00024, 0.00042, 0.05312, 0.1937, 0.21139, 0.19442, 0.1578, 0.1554, 0.14715, 0.18582, 0.24648, 0.18724, 0.1461, 0.15222, 0.15932, 0.15114, 0.14747, 0.14891, 0.15282, 0.1538, 0.15362, 0.15998, 0.15725, 0.16337, 0.14931, 0.13763, 0.13972, 0.14117, 0.14147, 0.15007, 0.157, 0.16051, 0.16221, 0.18065, 0.14604, 0.07912, 0.1071, 0.20763, 0.24029, 0.19915, 0.14692, 0.18461, 0.19063, 0.18459, 0.15017, 0.13988, 0.08639, 0.03915, 0.03605, 0.09377, 0.11053, 0.12343, 0.12109, 0.10781, 0.11064, 0.11193, 0.10563, 0.1098, 0.10581, 0.10694, 0.11249, 0.1334, 0.13543, 0.14087, 0.16203, 0.14521, 0.13053, 0.12848, 0.14461, 0.12817, 0.13978, 0.12296, 0.13632, 0.13521, 0.12011, 0.12219, 0.11914, 0.12655, 0.10543, 0.11889, 0.11759, 0.11499, 0.10994, 0.11466, 0.11107, 0.11212, 0.09998, 0.11549, 0.1048, 0.1114, 0.10966, 0.1063, 0.09293, 0.08436, 0.07895, 0.06734, 0.03944, 0.02604, 0.02086, 0.01822, 0.01291, 0.01212, 0.00432, 0.00243, 0.00092, 0.00043, 0.00026, 0.00013, 5e-05, 6e-05, 5e-05, 4e-05, 3e-05, 3e-05, 2e-05, 2e-05, 0.00012, 0.0457, 0.09729 ], "comparison": { "original": "Que ambuل", "retranscribed": "क्यों हम टुकड़ों में जिए", "reference_tokens": [ "que", "ambuل" ], "hypothesis_tokens": [ "क्यों", "हम", "टुकड़ों", "में", "जिए" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 3, "hits": 0, "reference_words": 2, "hypothesis_words": 5, "edits": 5 }, "wer": 2.5, "wer_percent": 250.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "क्यों", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "हम", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "टुकड़ों", "reference_index": null, "hypothesis_index": 2 }, { "op": "substitute", "reference": "que", "hypothesis": "में", "reference_index": 0, "hypothesis_index": 3 }, { "op": "substitute", "reference": "ambuل", "hypothesis": "जिए", "reference_index": 1, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.24648, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Happy", "emotion_confidence": 0.40113624930381775, "duration_seconds": 2.0130000000000052, "mos": 3.9292, "audio_variant": "original", "original_transcript_raw": "마이소니", "original_transcript": "마이소니", "retranscribed_transcript": "माही सोने", "backend": "bodhan", "emotion_analyzed_seconds": 2.013, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-163", "energy": { "value": 0.42578125, "bucket": "low" }, "audio_url": "audio/utterance-163.wav", "spectrogram_url": "spectrograms/utterance-163.png", "waveform": [ 0.00312, 0.00293, 0.00133, 0.00227, 0.01644, 0.06214, 0.09111, 0.09137, 0.09109, 0.08909, 0.08885, 0.09362, 0.10683, 0.13201, 0.17458, 0.20149, 0.25305, 0.26562, 0.26022, 0.22372, 0.23951, 0.27629, 0.27216, 0.27431, 0.28798, 0.33746, 0.32669, 0.22101, 0.20675, 0.13432, 0.10364, 0.10115, 0.09502, 0.10606, 0.13138, 0.16361, 0.17666, 0.27244, 0.31817, 0.29767, 0.28373, 0.27394, 0.26087, 0.22464, 0.21871, 0.21365, 0.2086, 0.21423, 0.2166, 0.20646, 0.16773, 0.12566, 0.09048, 0.04505, 0.03989, 0.04222, 0.04999, 0.04633, 0.04252, 0.06573, 0.09089, 0.07296, 0.10605, 0.12537, 0.11074, 0.10865, 0.09574, 0.06304, 0.04019, 0.02865, 0.01489, 0.04988, 0.14088, 0.15369, 0.1573, 0.15941, 0.15953, 0.15597, 0.15507, 0.15709, 0.15341, 0.15214, 0.15382, 0.15435, 0.15336, 0.14798, 0.14474, 0.1381, 0.14538, 0.14805, 0.15398, 0.15952, 0.15889, 0.16311, 0.14793, 0.14271, 0.14807, 0.13947, 0.12093, 0.14611, 0.14449, 0.13723, 0.14465, 0.15394, 0.18346, 0.17693, 0.17526, 0.17224, 0.17218, 0.17216, 0.15952, 0.14366, 0.11847, 0.10231, 0.08432, 0.08354, 0.1125, 0.13275, 0.13188, 0.11976, 0.12106, 0.11968, 0.10801, 0.10396, 0.09139, 0.0802, 0.07692, 0.0684, 0.06551, 0.06525, 0.0637, 0.06351, 0.0613, 0.06192, 0.06452, 0.06438, 0.06722, 0.06643, 0.06972, 0.07121, 0.07168, 0.07058, 0.07096, 0.07345, 0.07846, 0.07146, 0.07692, 0.07683, 0.06571, 0.06674, 0.07326, 0.06778, 0.06795, 0.06376, 0.0632, 0.05837, 0.04816, 0.0459, 0.04317, 0.04236, 0.04082, 0.04176, 0.04082, 0.03496, 0.03173, 0.02704, 0.02424, 0.02438, 0.02461, 0.02121, 0.0196, 0.01598, 0.01261, 0.0058, 0.00159, 0.00201, 0.00143, 0.00105, 0.00103, 0.00083 ], "comparison": { "original": "마이소니", "retranscribed": "माही सोने", "reference_tokens": [ "마이소니" ], "hypothesis_tokens": [ "माही", "सोने" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 1, "hits": 0, "reference_words": 1, "hypothesis_words": 2, "edits": 2 }, "wer": 2.0, "wer_percent": 200.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "माही", "reference_index": null, "hypothesis_index": 0 }, { "op": "substitute", "reference": "마이소니", "hypothesis": "सोने", "reference_index": 0, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.33746, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Happy", "emotion_confidence": 0.7364447712898254, "duration_seconds": 3.036999999999992, "mos": 3.1982, "audio_variant": "cleaned", "original_transcript_raw": "मैं उसे बहुत पसंद करती हूँ ही इस माइ बेस्ट फ्रेंड। ", "original_transcript": "मैं उसे बहुत पसंद करती हूँ ही इस माइ बेस्ट फ्रेंड।", "retranscribed_transcript": "मैं उसे बहुत पसंद करती हूँ ही इज़ माई बेस्ट फ्रेंड", "backend": "bodhan", "emotion_analyzed_seconds": 3.037, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-164", "energy": { "value": 0.50390625, "bucket": "low" }, "audio_url": "audio/utterance-164.wav", "spectrogram_url": "spectrograms/utterance-164.png", "waveform": [ 0.18606, 0.11958, 0.09229, 0.28572, 0.3044, 0.48121, 0.51011, 0.52101, 0.56181, 0.56752, 0.52607, 0.47818, 0.23455, 0.0307, 0.02519, 0.06959, 0.0761, 0.40017, 0.45726, 0.22999, 0.12759, 0.18973, 0.23657, 0.28666, 0.24395, 0.22815, 0.25502, 0.36747, 0.37917, 0.34162, 0.05802, 0.00955, 0.00594, 0.00462, 0.05481, 0.43969, 0.2608, 0.21972, 0.13777, 0.0261, 0.04014, 0.04961, 0.0423, 0.13188, 0.16238, 0.14108, 0.16793, 0.17576, 0.13904, 0.06589, 0.01785, 0.43831, 0.24197, 0.05526, 0.15168, 0.15526, 0.06043, 0.03098, 0.01695, 0.00454, 0.00227, 0.00162, 0.08548, 0.07627, 0.05947, 0.07175, 0.05918, 0.07124, 0.07316, 0.08054, 0.08064, 0.07199, 0.04871, 0.02768, 0.01203, 0.01093, 0.00452, 0.00258, 0.00212, 0.00244, 0.00198, 0.0017, 0.0021, 0.00171, 0.00126, 0.00247, 0.00101, 0.00137, 0.00314, 0.00269, 0.00272, 0.00356, 0.00363, 0.00229, 0.00204, 0.00361, 0.00376, 0.00446, 0.00286, 0.00308, 0.00625, 0.00553, 0.0045, 0.00585, 0.00614, 0.00549, 0.00446, 0.00475, 0.00611, 0.00427, 0.0044, 0.00484, 0.00387, 0.00223, 0.00509, 0.00204, 0.00585, 0.00329, 0.01065, 0.01011, 0.01255, 0.01925, 0.02245, 0.04011, 0.28919, 0.36206, 0.34382, 0.23745, 0.11402, 0.07078, 0.02908, 0.22738, 0.39278, 0.44587, 0.4761, 0.23393, 0.44258, 0.16739, 0.07235, 0.03687, 0.01169, 0.0074, 0.08385, 0.45828, 0.28185, 0.34077, 0.2059, 0.16516, 0.10561, 0.08826, 0.05173, 0.04448, 0.08594, 0.12581, 0.10867, 0.10144, 0.0401, 0.01997, 0.01258, 0.01924, 0.06478, 0.21946, 0.27211, 0.21898, 0.18908, 0.1394, 0.09846, 0.07185, 0.085, 0.07751, 0.08343, 0.09234, 0.09109, 0.07175, 0.05767, 0.01707, 0.08344, 0.05587, 0.10007, 0.18527 ], "comparison": { "original": "मैं उसे बहुत पसंद करती हूँ ही इस माइ बेस्ट फ्रेंड।", "retranscribed": "मैं उसे बहुत पसंद करती हूँ ही इज़ माई बेस्ट फ्रेंड", "reference_tokens": [ "मैं", "उसे", "बहुत", "पसंद", "करती", "हूँ", "ही", "इस", "माइ", "बेस्ट", "फ्रेंड" ], "hypothesis_tokens": [ "मैं", "उसे", "बहुत", "पसंद", "करती", "हूँ", "ही", "इज़", "माई", "बेस्ट", "फ्रेंड" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 9, "reference_words": 11, "hypothesis_words": 11, "edits": 2 }, "wer": 0.18181818181818182, "wer_percent": 18.181818181818183, "alignment": [ { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "उसे", "hypothesis": "उसे", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "बहुत", "hypothesis": "बहुत", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "पसंद", "hypothesis": "पसंद", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "करती", "hypothesis": "करती", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "हूँ", "hypothesis": "हूँ", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "ही", "hypothesis": "ही", "reference_index": 6, "hypothesis_index": 6 }, { "op": "substitute", "reference": "इस", "hypothesis": "इज़", "reference_index": 7, "hypothesis_index": 7 }, { "op": "substitute", "reference": "माइ", "hypothesis": "माई", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "बेस्ट", "hypothesis": "बेस्ट", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "फ्रेंड", "hypothesis": "फ्रेंड", "reference_index": 10, "hypothesis_index": 10 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.56752, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Happy", "emotion_confidence": 0.6669619083404541, "duration_seconds": 3.737000000000023, "mos": 2.8175, "audio_variant": "cleaned", "original_transcript_raw": "खर तो शानदार चमका है थैंक यू गेस्ट जो आ रहे हैं और पॉलिले", "original_transcript": "खर तो शानदार चमका है थैंक यू गेस्ट जो आ रहे हैं और पॉलिले", "retranscribed_transcript": "घर तो शानदार चमकाया थैंक यू गेस्ट जो आ रहे हैं और टॉयलेट", "backend": "bodhan", "emotion_analyzed_seconds": 3.737, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-165", "energy": { "value": 0.56640625, "bucket": "medium" }, "audio_url": "audio/utterance-165.wav", "spectrogram_url": "spectrograms/utterance-165.png", "waveform": [ 0.16316, 0.05142, 0.06157, 0.22023, 0.39195, 0.14981, 0.11846, 0.06885, 0.30637, 0.48514, 0.5893, 0.42595, 0.18037, 0.19985, 0.21882, 0.17278, 0.3409, 0.49434, 0.40408, 0.41969, 0.44088, 0.35835, 0.35218, 0.32735, 0.18642, 0.36115, 0.70334, 0.7694, 0.37608, 0.33174, 0.19603, 0.02316, 0.08978, 0.45364, 0.48668, 0.37767, 0.28813, 0.3105, 0.1238, 0.23538, 0.37893, 0.60731, 0.5682, 0.41873, 0.24823, 0.13275, 0.06611, 0.05399, 0.0489, 0.0402, 0.05533, 0.07044, 0.12694, 0.30755, 0.46494, 0.44664, 0.26504, 0.19891, 0.17228, 0.16782, 0.1478, 0.05146, 0.09705, 0.05384, 0.04266, 0.05513, 0.27612, 0.30229, 0.26251, 0.2727, 0.28305, 0.27557, 0.26514, 0.19842, 0.16381, 0.08904, 0.06268, 0.01377, 0.00295, 0.00128, 0.00087, 0.00067, 0.00068, 0.00035, 0.00051, 0.00048, 0.0006, 0.0018, 0.04859, 0.06876, 0.06759, 0.04362, 0.061, 0.4508, 0.43868, 0.41797, 0.45575, 0.4059, 0.33609, 0.11055, 0.05543, 0.1008, 0.1007, 0.10322, 0.13245, 0.3342, 0.54995, 0.55517, 0.37576, 0.44857, 0.70234, 0.62679, 0.5937, 0.45133, 0.42214, 0.37835, 0.32027, 0.14939, 0.27942, 0.25483, 0.23319, 0.26188, 0.27158, 0.1758, 0.14511, 0.08006, 0.05614, 0.1702, 0.31192, 0.44916, 0.54786, 0.44154, 0.39811, 0.3782, 0.34083, 0.31304, 0.33208, 0.33853, 0.34601, 0.37346, 0.37653, 0.40418, 0.26753, 0.24635, 0.18975, 0.19542, 0.23129, 0.23633, 0.25858, 0.24923, 0.28481, 0.30759, 0.30507, 0.34142, 0.27478, 0.21335, 0.20489, 0.15764, 0.10145, 0.02509, 0.00231, 0.00231, 0.00936, 0.1525, 0.36411, 0.3496, 0.36109, 0.26611, 0.19734, 0.11876, 0.19528, 0.24037, 0.2037, 0.15625, 0.05593, 0.03277, 0.00306, 0.01295, 0.05564, 0.09655 ], "comparison": { "original": "खर तो शानदार चमका है थैंक यू गेस्ट जो आ रहे हैं और पॉलिले", "retranscribed": "घर तो शानदार चमकाया थैंक यू गेस्ट जो आ रहे हैं और टॉयलेट", "reference_tokens": [ "खर", "तो", "शानदार", "चमका", "है", "थैंक", "यू", "गेस्ट", "जो", "आ", "रहे", "हैं", "और", "पॉलिले" ], "hypothesis_tokens": [ "घर", "तो", "शानदार", "चमकाया", "थैंक", "यू", "गेस्ट", "जो", "आ", "रहे", "हैं", "और", "टॉयलेट" ], "counts": { "substitutions": 3, "deletions": 1, "insertions": 0, "hits": 10, "reference_words": 14, "hypothesis_words": 13, "edits": 4 }, "wer": 0.2857142857142857, "wer_percent": 28.57142857142857, "alignment": [ { "op": "substitute", "reference": "खर", "hypothesis": "घर", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "तो", "hypothesis": "तो", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "शानदार", "hypothesis": "शानदार", "reference_index": 2, "hypothesis_index": 2 }, { "op": "delete", "reference": "चमका", "hypothesis": null, "reference_index": 3, "hypothesis_index": null }, { "op": "substitute", "reference": "है", "hypothesis": "चमकाया", "reference_index": 4, "hypothesis_index": 3 }, { "op": "equal", "reference": "थैंक", "hypothesis": "थैंक", "reference_index": 5, "hypothesis_index": 4 }, { "op": "equal", "reference": "यू", "hypothesis": "यू", "reference_index": 6, "hypothesis_index": 5 }, { "op": "equal", "reference": "गेस्ट", "hypothesis": "गेस्ट", "reference_index": 7, "hypothesis_index": 6 }, { "op": "equal", "reference": "जो", "hypothesis": "जो", "reference_index": 8, "hypothesis_index": 7 }, { "op": "equal", "reference": "आ", "hypothesis": "आ", "reference_index": 9, "hypothesis_index": 8 }, { "op": "equal", "reference": "रहे", "hypothesis": "रहे", "reference_index": 10, "hypothesis_index": 9 }, { "op": "equal", "reference": "हैं", "hypothesis": "हैं", "reference_index": 11, "hypothesis_index": 10 }, { "op": "equal", "reference": "और", "hypothesis": "और", "reference_index": 12, "hypothesis_index": 11 }, { "op": "substitute", "reference": "पॉलिले", "hypothesis": "टॉयलेट", "reference_index": 13, "hypothesis_index": 12 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.7694, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Happy", "emotion_confidence": 0.4295255243778229, "duration_seconds": 4.811999999999983, "mos": 3.0657, "audio_variant": "original", "original_transcript_raw": "तो वो बरेली कॉलेज के प्रिंसिपल क्या नाम है उनका वर्मा वर्मा जी जानते होंगे। ", "original_transcript": "तो वो बरेली कॉलेज के प्रिंसिपल क्या नाम है उनका वर्मा वर्मा जी जानते होंगे।", "retranscribed_transcript": "तो वो बरेली कॉलेज के प्रिंसिपल क्या नाम है उनका वर्मा जी जानते हो", "backend": "bodhan", "emotion_analyzed_seconds": 4.812, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-166", "energy": { "value": 0.57421875, "bucket": "medium" }, "audio_url": "audio/utterance-166.wav", "spectrogram_url": "spectrograms/utterance-166.png", "waveform": [ 0.04988, 0.11171, 0.21854, 0.21485, 0.22989, 0.24442, 0.22468, 0.2291, 0.2204, 0.14819, 0.11587, 0.06422, 0.0592, 0.06574, 0.07, 0.1032, 0.14994, 0.17296, 0.19215, 0.16369, 0.19866, 0.17581, 0.16133, 0.17913, 0.19042, 0.17003, 0.09246, 0.05037, 0.07366, 0.05798, 0.03769, 0.03062, 0.02876, 0.03558, 0.03301, 0.16377, 0.13033, 0.09172, 0.07721, 0.2319, 0.22545, 0.20244, 0.20909, 0.18822, 0.14362, 0.15185, 0.144, 0.0626, 0.08844, 0.18499, 0.11634, 0.06337, 0.02989, 0.17865, 0.19411, 0.19227, 0.13329, 0.11517, 0.16861, 0.12341, 0.11066, 0.04436, 0.02994, 0.17947, 0.17956, 0.02031, 0.07313, 0.09236, 0.07615, 0.10268, 0.10171, 0.08888, 0.04507, 0.04426, 0.07477, 0.14487, 0.15526, 0.07808, 0.03621, 0.09866, 0.18013, 0.21209, 0.19348, 0.18125, 0.09325, 0.20879, 0.209, 0.17254, 0.11145, 0.12392, 0.13539, 0.13326, 0.11664, 0.11153, 0.12327, 0.09723, 0.13105, 0.20529, 0.22145, 0.21354, 0.20573, 0.18069, 0.19178, 0.18523, 0.19964, 0.20033, 0.19621, 0.09905, 0.08453, 0.07752, 0.17346, 0.19042, 0.16329, 0.04233, 0.05372, 0.10267, 0.12168, 0.16353, 0.20924, 0.19328, 0.19578, 0.14258, 0.1215, 0.07754, 0.20121, 0.1997, 0.16337, 0.11859, 0.06565, 0.07529, 0.08961, 0.07777, 0.05581, 0.02426, 0.01535, 0.02002, 0.01891, 0.01612, 0.01394, 0.01648, 0.01616, 0.01729, 0.02041, 0.02619, 0.08413, 0.08008, 0.23212, 0.22123, 0.2041, 0.16703, 0.09341, 0.09098, 0.03651, 0.02, 0.22573, 0.21652, 0.12913, 0.09852, 0.07298, 0.07443, 0.0762, 0.1184, 0.17538, 0.19478, 0.20446, 0.18669, 0.20904, 0.12954, 0.08775, 0.0691, 0.08134, 0.06502, 0.09898, 0.16273, 0.20074, 0.16623, 0.20074, 0.18454, 0.14023, 0.0591 ], "comparison": { "original": "तो वो बरेली कॉलेज के प्रिंसिपल क्या नाम है उनका वर्मा वर्मा जी जानते होंगे।", "retranscribed": "तो वो बरेली कॉलेज के प्रिंसिपल क्या नाम है उनका वर्मा जी जानते हो", "reference_tokens": [ "तो", "वो", "बरेली", "कॉलेज", "के", "प्रिंसिपल", "क्या", "नाम", "है", "उनका", "वर्मा", "वर्मा", "जी", "जानते", "होंगे" ], "hypothesis_tokens": [ "तो", "वो", "बरेली", "कॉलेज", "के", "प्रिंसिपल", "क्या", "नाम", "है", "उनका", "वर्मा", "जी", "जानते", "हो" ], "counts": { "substitutions": 1, "deletions": 1, "insertions": 0, "hits": 13, "reference_words": 15, "hypothesis_words": 14, "edits": 2 }, "wer": 0.13333333333333333, "wer_percent": 13.333333333333334, "alignment": [ { "op": "equal", "reference": "तो", "hypothesis": "तो", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "वो", "hypothesis": "वो", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "बरेली", "hypothesis": "बरेली", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "कॉलेज", "hypothesis": "कॉलेज", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "के", "hypothesis": "के", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "प्रिंसिपल", "hypothesis": "प्रिंसिपल", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "क्या", "hypothesis": "क्या", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "नाम", "hypothesis": "नाम", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "उनका", "hypothesis": "उनका", "reference_index": 9, "hypothesis_index": 9 }, { "op": "delete", "reference": "वर्मा", "hypothesis": null, "reference_index": 10, "hypothesis_index": null }, { "op": "equal", "reference": "वर्मा", "hypothesis": "वर्मा", "reference_index": 11, "hypothesis_index": 10 }, { "op": "equal", "reference": "जी", "hypothesis": "जी", "reference_index": 12, "hypothesis_index": 11 }, { "op": "equal", "reference": "जानते", "hypothesis": "जानते", "reference_index": 13, "hypothesis_index": 12 }, { "op": "substitute", "reference": "होंगे", "hypothesis": "हो", "reference_index": 14, "hypothesis_index": 13 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.24442, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Happy", "emotion_confidence": 0.44572728872299194, "duration_seconds": 1.7409999999999997, "mos": 2.9949, "audio_variant": "cleaned", "original_transcript_raw": "わ け が ら も え", "original_transcript": "わ け が ら も え", "retranscribed_transcript": "ओहो वाकई गर्म है", "backend": "bodhan", "emotion_analyzed_seconds": 1.741, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-167", "energy": { "value": 0.5546875, "bucket": "medium" }, "audio_url": "audio/utterance-167.wav", "spectrogram_url": "spectrograms/utterance-167.png", "waveform": [ 0.0671, 0.06294, 0.04929, 0.02834, 0.01222, 0.00161, 0.00134, 0.0012, 0.00074, 0.00071, 0.00056, 0.00055, 0.0005, 0.00014, 0.00019, 0.0001, 9e-05, 9e-05, 8e-05, 0.00016, 0.00064, 0.00386, 0.0929, 0.09966, 0.16366, 0.20074, 0.33534, 0.28543, 0.45239, 0.51417, 0.50514, 0.44637, 0.53374, 0.37214, 0.48509, 0.1826, 0.13839, 0.12592, 0.03081, 0.01517, 0.00571, 0.00533, 0.04913, 0.23104, 0.26049, 0.3082, 0.32654, 0.27534, 0.26505, 0.29882, 0.26589, 0.31276, 0.34939, 0.32582, 0.30334, 0.27055, 0.28209, 0.27436, 0.23346, 0.22403, 0.20046, 0.20239, 0.19608, 0.1855, 0.17319, 0.19649, 0.1608, 0.15383, 0.14085, 0.13816, 0.11418, 0.10354, 0.09022, 0.09454, 0.09294, 0.08213, 0.08903, 0.11372, 0.12477, 0.12941, 0.19625, 0.20109, 0.25029, 0.44175, 0.50017, 0.5393, 0.43078, 0.34799, 0.37847, 0.42592, 0.42895, 0.24762, 0.06428, 0.05795, 0.00932, 0.0047, 0.07849, 0.0752, 0.16809, 0.18029, 0.2219, 0.26031, 0.36214, 0.2193, 0.28643, 0.24487, 0.22529, 0.23391, 0.20451, 0.18642, 0.15306, 0.14306, 0.10817, 0.09009, 0.07326, 0.07875, 0.18402, 0.25684, 0.33989, 0.34943, 0.35448, 0.28158, 0.31491, 0.19839, 0.08942, 0.23576, 0.41847, 0.23292, 0.27283, 0.30377, 0.21022, 0.30813, 0.19765, 0.22344, 0.21496, 0.19648, 0.20188, 0.21553, 0.24639, 0.20583, 0.221, 0.16884, 0.03672, 0.0129, 0.00508, 0.01348, 0.01042, 0.02727, 0.06217, 0.08675, 0.04383, 0.28293, 0.18138, 0.15865, 0.16976, 0.26834, 0.2422, 0.14914, 0.35354, 0.26349, 0.19468, 0.17714, 0.15397, 0.06538, 0.03721, 0.03198, 0.01619, 0.01166, 0.00267, 0.00077, 0.00032, 0.00024, 0.00015, 0.00013, 0.00012, 0.00062, 0.00155, 0.00163, 0.00339, 0.00344 ], "comparison": { "original": "わ け が ら も え", "retranscribed": "ओहो वाकई गर्म है", "reference_tokens": [ "わ", "け", "が", "ら", "も", "え" ], "hypothesis_tokens": [ "ओहो", "वाकई", "गर्म", "है" ], "counts": { "substitutions": 4, "deletions": 2, "insertions": 0, "hits": 0, "reference_words": 6, "hypothesis_words": 4, "edits": 6 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "delete", "reference": "わ", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "delete", "reference": "け", "hypothesis": null, "reference_index": 1, "hypothesis_index": null }, { "op": "substitute", "reference": "が", "hypothesis": "ओहो", "reference_index": 2, "hypothesis_index": 0 }, { "op": "substitute", "reference": "ら", "hypothesis": "वाकई", "reference_index": 3, "hypothesis_index": 1 }, { "op": "substitute", "reference": "も", "hypothesis": "गर्म", "reference_index": 4, "hypothesis_index": 2 }, { "op": "substitute", "reference": "え", "hypothesis": "है", "reference_index": 5, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.5393, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Happy", "emotion_confidence": 0.3026254177093506, "duration_seconds": 5.528999999999996, "mos": 3.1573, "audio_variant": "cleaned", "original_transcript_raw": "मैंने तो लागे से कि मेरे जो बच्चे हैं ना वो फुटबॉलर बनेगा हर मन नहीं। ", "original_transcript": "मैंने तो लागे से कि मेरे जो बच्चे हैं ना वो फुटबॉलर बनेगा हर मन नहीं।", "retranscribed_transcript": "मने तो लागे से कि मेरा जो बच्चा है ना वो फुटबॉलर बनेगा हर महीने", "backend": "bodhan", "emotion_analyzed_seconds": 5.529, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-168", "energy": { "value": 0.734375, "bucket": "high" }, "audio_url": "audio/utterance-168.wav", "spectrogram_url": "spectrograms/utterance-168.png", "waveform": [ 0.20102, 0.2872, 0.43808, 0.60556, 0.5593, 0.49435, 0.35534, 0.26708, 0.47768, 0.44817, 0.43453, 0.15845, 0.01484, 0.33317, 0.45412, 0.32988, 0.30552, 0.44342, 0.58469, 0.53087, 0.36625, 0.32653, 0.21713, 0.13362, 0.15439, 0.3988, 0.44408, 0.45133, 0.40677, 0.27287, 0.13891, 0.11037, 0.09131, 0.07193, 0.54785, 0.45271, 0.43329, 0.51943, 0.50178, 0.58331, 0.57507, 0.29734, 0.24932, 0.18315, 0.17257, 0.18424, 0.14992, 0.04529, 0.02314, 0.00162, 0.00038, 0.0535, 0.14904, 0.24384, 0.36615, 0.31653, 0.32079, 0.33986, 0.37255, 0.39183, 0.2184, 0.08178, 0.01196, 0.00046, 0.0003, 0.00016, 0.00014, 0.25275, 0.5391, 0.43, 0.2367, 0.29691, 0.31496, 0.34319, 0.33477, 0.47427, 0.51994, 0.49064, 0.43595, 0.45834, 0.44137, 0.38368, 0.14381, 0.55443, 0.49024, 0.31492, 0.13627, 0.20694, 0.59066, 0.33965, 0.07645, 0.0031, 0.0011, 0.04142, 0.12608, 0.12556, 0.35498, 0.46485, 0.47592, 0.51839, 0.47959, 0.39794, 0.32171, 0.52521, 0.52999, 0.35273, 0.29785, 0.23897, 0.18234, 0.10072, 0.00604, 0.01659, 0.19199, 0.25994, 0.23361, 0.24955, 0.22034, 0.08316, 0.00102, 0.01929, 0.4056, 0.48914, 0.34814, 0.25513, 0.06068, 0.0426, 0.05356, 0.09414, 0.06865, 0.54048, 0.48714, 0.20301, 0.17631, 0.47043, 0.17435, 0.17981, 0.4749, 0.41408, 0.42095, 0.48858, 0.3045, 0.55095, 0.58283, 0.36453, 0.4631, 0.41171, 0.15368, 0.524, 0.54854, 0.39513, 0.59757, 0.56348, 0.4827, 0.3747, 0.16246, 0.30148, 0.45045, 0.42231, 0.31705, 0.34317, 0.33834, 0.37558, 0.40829, 0.37864, 0.39205, 0.39962, 0.20605, 0.07691, 0.13313, 0.25557, 0.25263, 0.22146, 0.10234, 0.10317, 0.17002, 0.18716, 0.17579, 0.15598, 0.08511, 0.02298 ], "comparison": { "original": "मैंने तो लागे से कि मेरे जो बच्चे हैं ना वो फुटबॉलर बनेगा हर मन नहीं।", "retranscribed": "मने तो लागे से कि मेरा जो बच्चा है ना वो फुटबॉलर बनेगा हर महीने", "reference_tokens": [ "मैंने", "तो", "लागे", "से", "कि", "मेरे", "जो", "बच्चे", "हैं", "ना", "वो", "फुटबॉलर", "बनेगा", "हर", "मन", "नहीं" ], "hypothesis_tokens": [ "मने", "तो", "लागे", "से", "कि", "मेरा", "जो", "बच्चा", "है", "ना", "वो", "फुटबॉलर", "बनेगा", "हर", "महीने" ], "counts": { "substitutions": 5, "deletions": 1, "insertions": 0, "hits": 10, "reference_words": 16, "hypothesis_words": 15, "edits": 6 }, "wer": 0.375, "wer_percent": 37.5, "alignment": [ { "op": "substitute", "reference": "मैंने", "hypothesis": "मने", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "तो", "hypothesis": "तो", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "लागे", "hypothesis": "लागे", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "से", "hypothesis": "से", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "कि", "hypothesis": "कि", "reference_index": 4, "hypothesis_index": 4 }, { "op": "substitute", "reference": "मेरे", "hypothesis": "मेरा", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "जो", "hypothesis": "जो", "reference_index": 6, "hypothesis_index": 6 }, { "op": "substitute", "reference": "बच्चे", "hypothesis": "बच्चा", "reference_index": 7, "hypothesis_index": 7 }, { "op": "substitute", "reference": "हैं", "hypothesis": "है", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "ना", "hypothesis": "ना", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "वो", "hypothesis": "वो", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "फुटबॉलर", "hypothesis": "फुटबॉलर", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "बनेगा", "hypothesis": "बनेगा", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "हर", "hypothesis": "हर", "reference_index": 13, "hypothesis_index": 13 }, { "op": "delete", "reference": "मन", "hypothesis": null, "reference_index": 14, "hypothesis_index": null }, { "op": "substitute", "reference": "नहीं", "hypothesis": "महीने", "reference_index": 15, "hypothesis_index": 14 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.60556, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Happy", "emotion_confidence": 0.27121177315711975, "duration_seconds": 2.98599999999999, "mos": 2.8689, "audio_variant": "cleaned", "original_transcript_raw": "벗은지 앞서 복나", "original_transcript": "벗은지 앞서 복나", "retranscribed_transcript": "हप्पू सिंह जी आप सब लोग ज़िंदा हैं", "backend": "bodhan", "emotion_analyzed_seconds": 2.986, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-169", "energy": { "value": 0.6015625, "bucket": "high" }, "audio_url": "audio/utterance-169.wav", "spectrogram_url": "spectrograms/utterance-169.png", "waveform": [ 0.01987, 0.03564, 0.04302, 0.17934, 0.50827, 0.5036, 0.07058, 0.03682, 0.01709, 0.01658, 0.11278, 0.21646, 0.20791, 0.09985, 0.06955, 0.0626, 0.18069, 0.29465, 0.28545, 0.24462, 0.2308, 0.22001, 0.21113, 0.19364, 0.26917, 0.42995, 0.49041, 0.44998, 0.34038, 0.30342, 0.27379, 0.16811, 0.08248, 0.01572, 0.00181, 0.0005, 0.0003, 0.00025, 0.00017, 0.00015, 0.00012, 8e-05, 7e-05, 7e-05, 6e-05, 6e-05, 5e-05, 5e-05, 6e-05, 4e-05, 5e-05, 4e-05, 4e-05, 4e-05, 5e-05, 5e-05, 5e-05, 4e-05, 4e-05, 0.00015, 0.00681, 0.05914, 0.18964, 0.10467, 0.06828, 0.03495, 0.0325, 0.00228, 0.0004, 0.06558, 0.10204, 0.16094, 0.18312, 0.2459, 0.13064, 0.1239, 0.2474, 0.33117, 0.5535, 0.57738, 0.42498, 0.34173, 0.23767, 0.09295, 0.14817, 0.12714, 0.28542, 0.41308, 0.60766, 0.43066, 0.38715, 0.27686, 0.23041, 0.15323, 0.12765, 0.27433, 0.63346, 0.42328, 0.47112, 0.33731, 0.24674, 0.09477, 0.09104, 0.00933, 0.13683, 0.22324, 0.44647, 0.59579, 0.49882, 0.49156, 0.47403, 0.05543, 0.01953, 0.01721, 0.0458, 0.07383, 0.06381, 0.06965, 0.0617, 0.30938, 0.45412, 0.23589, 0.15581, 0.22642, 0.38245, 0.41307, 0.47448, 0.44535, 0.26307, 0.08331, 0.02359, 0.03274, 0.03437, 0.05316, 0.05542, 0.04677, 0.06143, 0.04701, 0.09387, 0.20387, 0.23868, 0.23739, 0.2911, 0.25434, 0.24666, 0.17897, 0.11637, 0.11389, 0.17229, 0.42864, 0.41786, 0.39853, 0.25802, 0.27105, 0.25425, 0.26822, 0.27725, 0.21254, 0.6395, 0.57477, 0.55406, 0.59403, 0.59932, 0.53027, 0.5208, 0.48427, 0.30034, 0.19781, 0.15852, 0.03313, 0.01405, 0.00391, 0.00103, 0.00022, 0.00013, 9e-05, 8e-05, 0.00574, 0.03889, 0.02715 ], "comparison": { "original": "벗은지 앞서 복나", "retranscribed": "हप्पू सिंह जी आप सब लोग ज़िंदा हैं", "reference_tokens": [ "벗은지", "앞서", "복나" ], "hypothesis_tokens": [ "हप्पू", "सिंह", "जी", "आप", "सब", "लोग", "ज़िंदा", "हैं" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 5, "hits": 0, "reference_words": 3, "hypothesis_words": 8, "edits": 8 }, "wer": 2.6666666666666665, "wer_percent": 266.66666666666663, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "हप्पू", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "सिंह", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "जी", "reference_index": null, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "आप", "reference_index": null, "hypothesis_index": 3 }, { "op": "insert", "reference": null, "hypothesis": "सब", "reference_index": null, "hypothesis_index": 4 }, { "op": "substitute", "reference": "벗은지", "hypothesis": "लोग", "reference_index": 0, "hypothesis_index": 5 }, { "op": "substitute", "reference": "앞서", "hypothesis": "ज़िंदा", "reference_index": 1, "hypothesis_index": 6 }, { "op": "substitute", "reference": "복나", "hypothesis": "हैं", "reference_index": 2, "hypothesis_index": 7 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.6395, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Happy", "emotion_confidence": 0.4863883852958679, "duration_seconds": 3.958999999999996, "mos": 3.0872, "audio_variant": "original", "original_transcript_raw": "Я кстати, которые", "original_transcript": "Я кстати, которые", "retranscribed_transcript": "देखो शेफ भी कंफ्यूज हो गया लग रहा दही जैसा", "backend": "bodhan", "emotion_analyzed_seconds": 3.959, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-170", "energy": { "value": 0.71875, "bucket": "high" }, "audio_url": "audio/utterance-170.wav", "spectrogram_url": "spectrograms/utterance-170.png", "waveform": [ 0.05586, 0.08902, 0.27095, 0.41434, 0.39855, 0.5397, 0.48366, 0.45861, 0.31712, 0.11053, 0.10594, 0.37491, 0.5141, 0.41268, 0.3362, 0.12736, 0.11764, 0.27784, 0.43912, 0.16519, 0.38364, 0.54578, 0.47393, 0.42732, 0.46604, 0.13007, 0.0933, 0.11543, 0.25782, 0.22473, 0.40828, 0.47245, 0.18795, 0.08109, 0.21742, 0.44245, 0.43291, 0.15299, 0.24845, 0.22488, 0.14762, 0.15684, 0.74863, 0.52757, 0.56121, 0.38272, 0.20218, 0.25619, 0.28227, 0.15689, 0.22821, 0.4019, 0.3777, 0.4386, 0.40596, 0.21354, 0.15858, 0.25552, 0.46944, 0.45366, 0.44886, 0.49927, 0.56511, 0.49642, 0.46223, 0.43027, 0.28716, 0.07349, 0.04196, 0.0757, 0.18317, 0.40071, 0.48828, 0.55154, 0.55259, 0.36848, 0.40724, 0.41755, 0.38589, 0.37557, 0.27855, 0.12765, 0.17931, 0.13929, 0.22552, 0.15546, 0.14896, 0.29067, 0.42241, 0.49657, 0.50303, 0.39814, 0.3052, 0.14743, 0.35018, 0.50263, 0.43653, 0.27515, 0.38189, 0.43556, 0.46849, 0.43448, 0.30138, 0.11283, 0.07796, 0.26093, 0.36657, 0.38174, 0.46331, 0.49466, 0.32492, 0.25267, 0.20418, 0.08142, 0.08233, 0.21725, 0.46935, 0.38299, 0.36197, 0.29225, 0.11727, 0.089, 0.05767, 0.21052, 0.38229, 0.36787, 0.38251, 0.3751, 0.38561, 0.42033, 0.41045, 0.22797, 0.03286, 0.02308, 0.01737, 0.01475, 0.01333, 0.00983, 0.01176, 0.00901, 0.55181, 0.64386, 0.56648, 0.44471, 0.48059, 0.44578, 0.42816, 0.3996, 0.39343, 0.36016, 0.30143, 0.24008, 0.23257, 0.25228, 0.65794, 0.65577, 0.45442, 0.45044, 0.37812, 0.37019, 0.3355, 0.28314, 0.56981, 0.38385, 0.38336, 0.09585, 0.06393, 0.09194, 0.08575, 0.37214, 0.49282, 0.53081, 0.07783, 0.06601, 0.04878, 0.04476, 0.23397, 0.36262, 0.45354, 0.09268 ], "comparison": { "original": "Я кстати, которые", "retranscribed": "देखो शेफ भी कंफ्यूज हो गया लग रहा दही जैसा", "reference_tokens": [ "я", "кстати", "которые" ], "hypothesis_tokens": [ "देखो", "शेफ", "भी", "कंफ्यूज", "हो", "गया", "लग", "रहा", "दही", "जैसा" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 7, "hits": 0, "reference_words": 3, "hypothesis_words": 10, "edits": 10 }, "wer": 3.3333333333333335, "wer_percent": 333.33333333333337, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "देखो", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "शेफ", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "भी", "reference_index": null, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "कंफ्यूज", "reference_index": null, "hypothesis_index": 3 }, { "op": "insert", "reference": null, "hypothesis": "हो", "reference_index": null, "hypothesis_index": 4 }, { "op": "insert", "reference": null, "hypothesis": "गया", "reference_index": null, "hypothesis_index": 5 }, { "op": "insert", "reference": null, "hypothesis": "लग", "reference_index": null, "hypothesis_index": 6 }, { "op": "substitute", "reference": "я", "hypothesis": "रहा", "reference_index": 0, "hypothesis_index": 7 }, { "op": "substitute", "reference": "кстати", "hypothesis": "दही", "reference_index": 1, "hypothesis_index": 8 }, { "op": "substitute", "reference": "которые", "hypothesis": "जैसा", "reference_index": 2, "hypothesis_index": 9 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.74863, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Neutral", "emotion_confidence": 0.34637391567230225, "duration_seconds": 1.313999999999993, "mos": 3.0559, "audio_variant": "original", "original_transcript_raw": "मेरा याद है राज", "original_transcript": "मेरा याद है राज", "retranscribed_transcript": "मेरा यार है राजेश", "backend": "bodhan", "emotion_analyzed_seconds": 1.314, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-171", "energy": { "value": 0.515625, "bucket": "low" }, "audio_url": "audio/utterance-171.wav", "spectrogram_url": "spectrograms/utterance-171.png", "waveform": [ 0.16763, 0.23745, 0.27058, 0.28699, 0.31799, 0.31497, 0.31098, 0.36394, 0.34114, 0.34556, 0.30663, 0.28665, 0.29139, 0.34345, 0.34222, 0.32589, 0.35285, 0.3492, 0.35082, 0.34856, 0.35273, 0.35196, 0.3469, 0.2068, 0.32945, 0.30856, 0.32701, 0.26305, 0.26591, 0.25829, 0.25949, 0.24184, 0.21892, 0.24423, 0.2267, 0.2625, 0.25595, 0.24187, 0.25872, 0.29364, 0.33786, 0.32899, 0.29957, 0.34931, 0.35138, 0.34776, 0.33969, 0.33865, 0.33385, 0.34701, 0.33488, 0.22174, 0.33558, 0.33686, 0.33272, 0.21629, 0.34137, 0.33542, 0.33594, 0.33037, 0.24205, 0.3309, 0.34097, 0.33128, 0.32203, 0.3289, 0.32274, 0.35021, 0.34719, 0.34018, 0.31089, 0.22331, 0.22755, 0.05908, 0.09964, 0.08774, 0.03649, 0.0565, 0.07653, 0.10351, 0.11295, 0.05701, 0.06795, 0.06997, 0.06545, 0.04326, 0.03798, 0.04511, 0.07651, 0.06127, 0.10616, 0.12067, 0.12593, 0.11426, 0.1313, 0.13228, 0.05801, 0.12522, 0.09349, 0.09592, 0.11621, 0.12479, 0.08414, 0.12717, 0.18245, 0.07852, 0.16383, 0.16568, 0.1403, 0.1413, 0.12289, 0.11398, 0.09686, 0.06319, 0.03892, 0.03806, 0.0185, 0.01881, 0.01947, 0.01184, 0.01004, 0.01087, 0.01342, 0.01606, 0.03169, 0.03002, 0.03686, 0.04592, 0.06876, 0.10173, 0.13542, 0.11684, 0.14924, 0.24181, 0.28379, 0.29198, 0.34696, 0.32977, 0.35547, 0.33929, 0.34531, 0.33271, 0.31812, 0.30105, 0.26058, 0.2084, 0.12743, 0.12845, 0.0914, 0.16065, 0.10859, 0.1679, 0.19284, 0.16398, 0.18958, 0.17802, 0.18309, 0.20661, 0.13394, 0.17783, 0.14011, 0.12776, 0.11374, 0.11377, 0.10675, 0.08651, 0.12718, 0.11277, 0.10222, 0.11359, 0.07851, 0.1092, 0.07971, 0.065, 0.06137, 0.05849, 0.06655, 0.05184, 0.04241, 0.03215 ], "comparison": { "original": "मेरा याद है राज", "retranscribed": "मेरा यार है राजेश", "reference_tokens": [ "मेरा", "याद", "है", "राज" ], "hypothesis_tokens": [ "मेरा", "यार", "है", "राजेश" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 4, "hypothesis_words": 4, "edits": 2 }, "wer": 0.5, "wer_percent": 50.0, "alignment": [ { "op": "equal", "reference": "मेरा", "hypothesis": "मेरा", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "याद", "hypothesis": "यार", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 2, "hypothesis_index": 2 }, { "op": "substitute", "reference": "राज", "hypothesis": "राजेश", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.36394, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Neutral", "emotion_confidence": 0.689402163028717, "duration_seconds": 1.3659999999999997, "mos": 3.2318, "audio_variant": "cleaned", "original_transcript_raw": "अपने बच्चे हैं। ", "original_transcript": "अपने बच्चे हैं।", "retranscribed_transcript": "अपने बच्चे हैं", "backend": "bodhan", "emotion_analyzed_seconds": 1.366, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-172", "energy": { "value": 0.494140625, "bucket": "low" }, "audio_url": "audio/utterance-172.wav", "spectrogram_url": "spectrograms/utterance-172.png", "waveform": [ 0.00201, 0.00196, 0.00233, 0.00152, 0.00078, 0.0005, 0.00032, 0.00035, 0.0087, 0.32024, 0.68643, 0.66864, 0.64099, 0.47193, 0.3926, 0.39207, 0.03409, 0.02788, 0.00845, 0.00546, 0.00149, 0.00111, 0.00052, 0.00044, 0.00138, 0.00126, 0.01159, 0.01572, 0.36757, 0.41813, 0.20337, 0.27635, 0.26969, 0.28261, 0.30408, 0.31773, 0.30554, 0.63768, 0.65907, 0.60449, 0.52815, 0.55509, 0.48876, 0.36839, 0.17986, 0.07594, 0.10964, 0.08188, 0.08112, 0.06401, 0.05302, 0.07567, 0.24603, 0.31912, 0.3237, 0.39442, 0.36819, 0.19039, 0.15112, 0.09009, 0.01598, 0.00858, 0.00164, 0.00095, 0.00043, 0.00036, 0.00024, 0.00017, 0.00015, 0.00012, 0.00019, 0.02148, 0.01123, 0.00638, 0.08013, 0.22075, 0.19536, 0.19985, 0.13251, 0.07401, 0.26903, 0.55657, 0.53993, 0.57859, 0.52476, 0.4871, 0.50628, 0.39959, 0.37931, 0.33465, 0.32454, 0.26777, 0.24865, 0.14626, 0.14927, 0.13102, 0.13985, 0.14701, 0.22767, 0.26575, 0.38309, 0.39252, 0.481, 0.48233, 0.44091, 0.37188, 0.29051, 0.18125, 0.16207, 0.17713, 0.12417, 0.07058, 0.05864, 0.04996, 0.03175, 0.02013, 0.00924, 0.0048, 0.00168, 0.00049, 0.00033, 0.00025, 0.00023, 0.00023, 0.00021, 0.00019, 0.00018, 0.00016, 0.00015, 0.00012, 0.00012, 0.0001, 0.00011, 9e-05, 7e-05, 8e-05, 8e-05, 7e-05, 7e-05, 7e-05, 6e-05, 6e-05, 7e-05, 6e-05, 6e-05, 5e-05, 5e-05, 6e-05, 8e-05, 0.0001, 0.00011, 0.00012, 0.00011, 0.0001, 9e-05, 9e-05, 9e-05, 7e-05, 6e-05, 7e-05, 5e-05, 6e-05, 5e-05, 4e-05, 4e-05, 4e-05, 5e-05, 3e-05, 3e-05, 5e-05, 3e-05, 4e-05, 4e-05, 0.0002, 0.00041, 0.00111, 0.00136, 0.0013, 0.00212, 0.004 ], "comparison": { "original": "अपने बच्चे हैं।", "retranscribed": "अपने बच्चे हैं", "reference_tokens": [ "अपने", "बच्चे", "हैं" ], "hypothesis_tokens": [ "अपने", "बच्चे", "हैं" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 3, "reference_words": 3, "hypothesis_words": 3, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "अपने", "hypothesis": "अपने", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "बच्चे", "hypothesis": "बच्चे", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "हैं", "hypothesis": "हैं", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.68643, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Neutral", "emotion_confidence": 0.6757698059082031, "duration_seconds": 4.522000000000006, "mos": 3.5132, "audio_variant": "original", "original_transcript_raw": "ये जो नकली हीरे हैं इसमें इनको निकाल दो और ये जो असली है इनमें जड़ दो। ", "original_transcript": "ये जो नकली हीरे हैं इसमें इनको निकाल दो और ये जो असली है इनमें जड़ दो।", "retranscribed_transcript": "ये जो नकली हीरे हैं इसमें इनको निकाल दो और ये जो असली हैं इनमें जड़ दो", "backend": "bodhan", "emotion_analyzed_seconds": 4.522, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-173", "energy": { "value": 0.49609375, "bucket": "low" }, "audio_url": "audio/utterance-173.wav", "spectrogram_url": "spectrograms/utterance-173.png", "waveform": [ 0.13385, 0.31652, 0.36754, 0.42363, 0.43319, 0.40149, 0.2567, 0.19553, 0.32482, 0.47168, 0.44349, 0.3325, 0.15106, 0.14268, 0.30805, 0.38895, 0.40961, 0.46507, 0.47413, 0.41193, 0.22529, 0.02837, 0.00975, 0.25985, 0.27913, 0.35439, 0.40601, 0.35585, 0.33024, 0.41332, 0.40386, 0.41952, 0.19124, 0.43496, 0.4469, 0.4125, 0.42407, 0.40422, 0.39923, 0.38939, 0.30723, 0.22274, 0.20508, 0.1767, 0.08759, 0.31294, 0.46508, 0.48455, 0.40329, 0.34068, 0.17387, 0.15772, 0.15242, 0.10591, 0.13111, 0.13095, 0.11375, 0.09771, 0.24805, 0.26008, 0.2821, 0.28286, 0.2777, 0.22191, 0.21494, 0.13085, 0.09106, 0.05135, 0.04097, 0.00975, 0.00632, 0.00405, 0.00408, 0.00767, 0.28934, 0.44887, 0.39995, 0.33313, 0.1608, 0.23983, 0.46754, 0.47403, 0.3683, 0.35583, 0.39557, 0.42066, 0.24238, 0.08928, 0.11436, 0.29677, 0.4325, 0.4238, 0.40105, 0.17363, 0.16676, 0.18116, 0.12211, 0.11253, 0.11664, 0.08151, 0.11644, 0.07315, 0.05613, 0.04796, 0.02545, 0.01669, 0.02196, 0.02275, 0.15727, 0.35609, 0.49132, 0.44582, 0.39471, 0.34989, 0.33413, 0.33084, 0.3656, 0.37455, 0.33404, 0.19413, 0.11711, 0.2932, 0.4291, 0.48472, 0.45118, 0.39777, 0.19401, 0.10179, 0.09334, 0.09518, 0.13155, 0.31503, 0.48136, 0.40543, 0.41435, 0.4004, 0.44783, 0.43293, 0.37929, 0.35989, 0.34229, 0.33813, 0.42675, 0.42443, 0.2516, 0.17442, 0.21102, 0.28819, 0.36874, 0.36265, 0.27919, 0.20323, 0.18574, 0.07198, 0.15793, 0.1649, 0.111, 0.07142, 0.07416, 0.02396, 0.01265, 0.01008, 0.00701, 0.00582, 0.00254, 0.00213, 0.00236, 0.00532, 0.0121, 0.02395, 0.02145, 0.02655, 0.0292, 0.02328, 0.02134, 0.01972, 0.02178, 0.01808, 0.0149, 0.00942 ], "comparison": { "original": "ये जो नकली हीरे हैं इसमें इनको निकाल दो और ये जो असली है इनमें जड़ दो।", "retranscribed": "ये जो नकली हीरे हैं इसमें इनको निकाल दो और ये जो असली हैं इनमें जड़ दो", "reference_tokens": [ "ये", "जो", "नकली", "हीरे", "हैं", "इसमें", "इनको", "निकाल", "दो", "और", "ये", "जो", "असली", "है", "इनमें", "जड़", "दो" ], "hypothesis_tokens": [ "ये", "जो", "नकली", "हीरे", "हैं", "इसमें", "इनको", "निकाल", "दो", "और", "ये", "जो", "असली", "हैं", "इनमें", "जड़", "दो" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 16, "reference_words": 17, "hypothesis_words": 17, "edits": 1 }, "wer": 0.058823529411764705, "wer_percent": 5.88235294117647, "alignment": [ { "op": "equal", "reference": "ये", "hypothesis": "ये", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "जो", "hypothesis": "जो", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "नकली", "hypothesis": "नकली", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "हीरे", "hypothesis": "हीरे", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "हैं", "hypothesis": "हैं", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "इसमें", "hypothesis": "इसमें", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "इनको", "hypothesis": "इनको", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "निकाल", "hypothesis": "निकाल", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "दो", "hypothesis": "दो", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "और", "hypothesis": "और", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "ये", "hypothesis": "ये", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "जो", "hypothesis": "जो", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "असली", "hypothesis": "असली", "reference_index": 12, "hypothesis_index": 12 }, { "op": "substitute", "reference": "है", "hypothesis": "हैं", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "इनमें", "hypothesis": "इनमें", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "जड़", "hypothesis": "जड़", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "दो", "hypothesis": "दो", "reference_index": 16, "hypothesis_index": 16 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.49132, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Neutral", "emotion_confidence": 0.4947943091392517, "duration_seconds": 2.969999999999999, "mos": 3.5273, "audio_variant": "cleaned", "original_transcript_raw": "अरे बहुत अच्छा किया यार मैं मैं ढूंढ ही रहा था ऐसे", "original_transcript": "अरे बहुत अच्छा किया यार मैं मैं ढूंढ ही रहा था ऐसे", "retranscribed_transcript": "दे देना है अरे बहुत अच्छा किया यार मैं मैं ढूंढ ही रहा था ऐसे", "backend": "bodhan", "emotion_analyzed_seconds": 2.97, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-174", "energy": { "value": 0.578125, "bucket": "medium" }, "audio_url": "audio/utterance-174.wav", "spectrogram_url": "spectrograms/utterance-174.png", "waveform": [ 0.18125, 0.10258, 0.3343, 0.56945, 0.88539, 0.9808, 0.76262, 0.30187, 0.52081, 0.91918, 0.97065, 1.05491, 0.87114, 0.82245, 0.53178, 0.95752, 0.97397, 0.8684, 0.89988, 0.86297, 0.7776, 0.56093, 0.39801, 0.2834, 0.17746, 0.12654, 0.02522, 0.01064, 0.00602, 0.00362, 0.00297, 0.0025, 0.00159, 0.00058, 0.00031, 0.00022, 0.00017, 0.00014, 0.00012, 0.00011, 0.0001, 9e-05, 0.00011, 0.00026, 0.0684, 0.38022, 0.60835, 0.68056, 0.81243, 0.84754, 0.82033, 0.14062, 0.12102, 0.10127, 0.06571, 0.27437, 0.62617, 0.70711, 0.80921, 0.84373, 0.7759, 0.39151, 0.82906, 0.85302, 0.74754, 0.11533, 0.01304, 0.07788, 0.19778, 0.24431, 0.20034, 0.82741, 0.87318, 0.90722, 0.76426, 0.16146, 0.16795, 0.26745, 0.79262, 0.86411, 0.97846, 0.9136, 0.94027, 0.89229, 0.89645, 0.91509, 0.88776, 0.903, 0.92913, 0.91112, 0.94368, 0.89083, 0.81399, 0.52265, 0.71114, 0.61354, 0.33389, 0.37222, 0.38158, 0.65852, 0.85352, 0.86729, 0.90675, 0.96027, 0.99788, 0.80232, 0.78428, 0.7999, 0.90684, 0.89622, 0.82011, 0.55808, 0.1895, 0.12078, 0.11642, 0.10104, 0.04835, 0.02019, 0.00522, 0.00205, 0.0007, 0.00119, 0.00734, 0.04414, 0.07475, 0.11008, 0.10173, 0.30177, 0.66949, 0.84501, 0.87852, 0.86109, 0.76106, 0.13599, 0.09845, 0.13657, 0.20999, 0.2388, 0.29969, 0.34602, 0.31857, 0.33766, 0.86205, 0.88647, 0.91459, 0.93973, 0.6919, 0.85598, 0.92317, 0.90181, 0.96319, 0.69859, 0.10198, 0.02332, 0.14581, 0.81371, 0.88522, 0.83916, 0.87156, 0.78518, 0.36015, 0.15896, 0.09045, 0.06869, 0.29492, 0.45801, 0.49388, 0.44417, 0.35058, 0.26371, 0.18795, 0.10752, 0.04519, 0.01308, 0.00087, 0.00017, 0.00034, 0.03806, 0.069, 0.1153 ], "comparison": { "original": "अरे बहुत अच्छा किया यार मैं मैं ढूंढ ही रहा था ऐसे", "retranscribed": "दे देना है अरे बहुत अच्छा किया यार मैं मैं ढूंढ ही रहा था ऐसे", "reference_tokens": [ "अरे", "बहुत", "अच्छा", "किया", "यार", "मैं", "मैं", "ढूंढ", "ही", "रहा", "था", "ऐसे" ], "hypothesis_tokens": [ "दे", "देना", "है", "अरे", "बहुत", "अच्छा", "किया", "यार", "मैं", "मैं", "ढूंढ", "ही", "रहा", "था", "ऐसे" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 3, "hits": 12, "reference_words": 12, "hypothesis_words": 15, "edits": 3 }, "wer": 0.25, "wer_percent": 25.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "दे", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "देना", "reference_index": null, "hypothesis_index": 1 }, { "op": "insert", "reference": null, "hypothesis": "है", "reference_index": null, "hypothesis_index": 2 }, { "op": "equal", "reference": "अरे", "hypothesis": "अरे", "reference_index": 0, "hypothesis_index": 3 }, { "op": "equal", "reference": "बहुत", "hypothesis": "बहुत", "reference_index": 1, "hypothesis_index": 4 }, { "op": "equal", "reference": "अच्छा", "hypothesis": "अच्छा", "reference_index": 2, "hypothesis_index": 5 }, { "op": "equal", "reference": "किया", "hypothesis": "किया", "reference_index": 3, "hypothesis_index": 6 }, { "op": "equal", "reference": "यार", "hypothesis": "यार", "reference_index": 4, "hypothesis_index": 7 }, { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 5, "hypothesis_index": 8 }, { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 6, "hypothesis_index": 9 }, { "op": "equal", "reference": "ढूंढ", "hypothesis": "ढूंढ", "reference_index": 7, "hypothesis_index": 10 }, { "op": "equal", "reference": "ही", "hypothesis": "ही", "reference_index": 8, "hypothesis_index": 11 }, { "op": "equal", "reference": "रहा", "hypothesis": "रहा", "reference_index": 9, "hypothesis_index": 12 }, { "op": "equal", "reference": "था", "hypothesis": "था", "reference_index": 10, "hypothesis_index": 13 }, { "op": "equal", "reference": "ऐसे", "hypothesis": "ऐसे", "reference_index": 11, "hypothesis_index": 14 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz float32 WAV", "source_peak_abs": 1.05491, "audio_sample_format": "float32" }, { "language": "Hindi", "emotion": "Neutral", "emotion_confidence": 0.39046239852905273, "duration_seconds": 1.5190000000000055, "mos": 3.0182, "audio_variant": "cleaned", "original_transcript_raw": "तम सबकी मौत लिखी हुई है। ", "original_transcript": "तम सबकी मौत लिखी हुई है।", "retranscribed_transcript": "तुम सबकी मौत लिखी हुई है", "backend": "bodhan", "emotion_analyzed_seconds": 1.519, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-175", "energy": { "value": 0.56640625, "bucket": "medium" }, "audio_url": "audio/utterance-175.wav", "spectrogram_url": "spectrograms/utterance-175.png", "waveform": [ 0.01514, 0.0747, 0.10651, 0.18865, 0.17115, 0.16889, 0.13178, 0.11935, 0.09397, 0.05209, 0.03886, 0.05249, 0.06565, 0.07621, 0.07314, 0.05912, 0.05521, 0.03389, 0.0184, 0.02002, 0.01636, 0.0196, 0.02142, 0.03599, 0.02747, 0.02372, 0.14116, 0.12797, 0.13261, 0.11841, 0.10548, 0.07961, 0.02957, 0.0083, 0.00287, 0.00113, 0.00048, 0.0002, 0.00016, 0.0001, 7e-05, 4e-05, 4e-05, 9e-05, 0.0005, 0.0074, 0.07689, 0.0823, 0.02454, 0.04809, 0.11552, 0.13431, 0.13149, 0.11691, 0.0769, 0.03976, 0.04347, 0.05661, 0.04258, 0.06318, 0.06511, 0.06216, 0.06461, 0.061, 0.0623, 0.05925, 0.06016, 0.06298, 0.0644, 0.06604, 0.10205, 0.11833, 0.1565, 0.17849, 0.17926, 0.11755, 0.11084, 0.09479, 0.11907, 0.12157, 0.10311, 0.05661, 0.01754, 0.01419, 0.00144, 0.00073, 0.00071, 0.00012, 0.00014, 8e-05, 7e-05, 0.00012, 0.00148, 0.0401, 0.02142, 0.02532, 0.0337, 0.01969, 0.02587, 0.04093, 0.03737, 0.06982, 0.09414, 0.09661, 0.05403, 0.03136, 0.01856, 0.00993, 0.00261, 0.00102, 0.00061, 0.0074, 0.07846, 0.03391, 0.04175, 0.04261, 0.04097, 0.04296, 0.03718, 0.01805, 0.05707, 0.04232, 0.03185, 0.03262, 0.03051, 0.02484, 0.01962, 0.01461, 0.01754, 0.02109, 0.02191, 0.02298, 0.02095, 0.03251, 0.03279, 0.05284, 0.02467, 0.05782, 0.04465, 0.02448, 0.01862, 0.0198, 0.02068, 0.01638, 0.01624, 0.01743, 0.01498, 0.0192, 0.0262, 0.02402, 0.02051, 0.02253, 0.0263, 0.0216, 0.02371, 0.02928, 0.02223, 0.02513, 0.02156, 0.02333, 0.02026, 0.02033, 0.01819, 0.01159, 0.00514, 0.00107, 0.00061, 0.00027, 0.00015, 7e-05, 6e-05, 5e-05, 4e-05, 3e-05, 0.00066, 0.00161, 0.00339, 0.00326, 0.00502, 0.00615 ], "comparison": { "original": "तम सबकी मौत लिखी हुई है।", "retranscribed": "तुम सबकी मौत लिखी हुई है", "reference_tokens": [ "तम", "सबकी", "मौत", "लिखी", "हुई", "है" ], "hypothesis_tokens": [ "तुम", "सबकी", "मौत", "लिखी", "हुई", "है" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 6, "hypothesis_words": 6, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "substitute", "reference": "तम", "hypothesis": "तुम", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "सबकी", "hypothesis": "सबकी", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "मौत", "hypothesis": "मौत", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "लिखी", "hypothesis": "लिखी", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "हुई", "hypothesis": "हुई", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.18865, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Neutral", "emotion_confidence": 0.42671215534210205, "duration_seconds": 2.730000000000018, "mos": 3.4019, "audio_variant": "cleaned", "original_transcript_raw": "माफ़ कीजिएगा। मुझे तुम्हें खाना खाने का कोई शौक", "original_transcript": "माफ़ कीजिएगा। मुझे तुम्हें खाना खाने का कोई शौक", "retranscribed_transcript": "माफ़ कीजिएगा मुझे इस तरह खाना खाने का कोई शौक़ नहीं", "backend": "bodhan", "emotion_analyzed_seconds": 2.73, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-176", "energy": { "value": 0.56640625, "bucket": "medium" }, "audio_url": "audio/utterance-176.wav", "spectrogram_url": "spectrograms/utterance-176.png", "waveform": [ 0.03079, 0.06392, 0.08249, 0.09416, 0.07572, 0.13196, 0.13136, 0.16103, 0.17913, 0.22546, 0.61972, 0.6722, 0.54826, 0.57201, 0.61513, 0.55147, 0.59518, 0.53819, 0.51274, 0.31364, 0.07584, 0.01817, 0.01317, 0.00532, 0.00296, 0.00179, 0.00143, 0.00099, 0.03759, 0.03581, 0.04558, 0.14653, 0.29406, 0.36852, 0.2998, 0.24439, 0.18092, 0.11579, 0.08374, 0.10274, 0.10877, 0.31173, 0.3904, 0.5275, 0.52664, 0.48658, 0.3848, 0.40953, 0.28906, 0.1737, 0.1661, 0.28323, 0.66834, 0.57877, 0.63075, 0.50935, 0.45385, 0.26176, 0.16209, 0.05212, 0.04915, 0.05605, 0.05812, 0.07243, 0.17012, 0.26173, 0.39585, 0.39292, 0.3025, 0.27034, 0.35963, 0.3991, 0.41492, 0.41456, 0.31463, 0.10201, 0.02898, 0.01975, 0.01429, 0.01504, 0.00971, 0.00631, 0.05759, 0.06032, 0.15306, 0.23074, 0.40177, 0.4885, 0.5007, 0.24942, 0.27577, 0.02143, 0.00375, 0.04998, 0.16455, 0.22831, 0.04969, 0.03507, 0.0809, 0.38137, 0.36436, 0.45171, 0.44922, 0.15807, 0.28737, 0.61785, 0.48911, 0.38978, 0.25599, 0.03368, 0.01167, 0.01595, 0.01417, 0.15034, 0.25519, 0.3928, 0.4487, 0.41995, 0.13355, 0.12651, 0.36012, 0.37949, 0.34772, 0.22081, 0.1311, 0.05646, 0.01671, 0.12994, 0.48277, 0.58743, 0.44481, 0.28646, 0.07862, 0.03109, 0.00248, 0.001, 0.00069, 0.00042, 0.00037, 0.00026, 0.0003, 0.00057, 0.05131, 0.04454, 0.11532, 0.21742, 0.30541, 0.33326, 0.32796, 0.34368, 0.28164, 0.26016, 0.32787, 0.3162, 0.25491, 0.15618, 0.09405, 0.10303, 0.14679, 0.13977, 0.15265, 0.15629, 0.11207, 0.0754, 0.03425, 0.09197, 0.08328, 0.10785, 0.10309, 0.04621, 0.04634, 0.03255, 0.01289, 0.00227, 0.0006, 0.0002, 0.00217, 0.0064, 0.0086, 0.015 ], "comparison": { "original": "माफ़ कीजिएगा। मुझे तुम्हें खाना खाने का कोई शौक", "retranscribed": "माफ़ कीजिएगा मुझे इस तरह खाना खाने का कोई शौक़ नहीं", "reference_tokens": [ "माफ़", "कीजिएगा", "मुझे", "तुम्हें", "खाना", "खाने", "का", "कोई", "शौक" ], "hypothesis_tokens": [ "माफ़", "कीजिएगा", "मुझे", "इस", "तरह", "खाना", "खाने", "का", "कोई", "शौक़", "नहीं" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 2, "hits": 7, "reference_words": 9, "hypothesis_words": 11, "edits": 4 }, "wer": 0.4444444444444444, "wer_percent": 44.44444444444444, "alignment": [ { "op": "equal", "reference": "माफ़", "hypothesis": "माफ़", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "कीजिएगा", "hypothesis": "कीजिएगा", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "मुझे", "hypothesis": "मुझे", "reference_index": 2, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "इस", "reference_index": null, "hypothesis_index": 3 }, { "op": "substitute", "reference": "तुम्हें", "hypothesis": "तरह", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "खाना", "hypothesis": "खाना", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "खाने", "hypothesis": "खाने", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "का", "hypothesis": "का", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "कोई", "hypothesis": "कोई", "reference_index": 7, "hypothesis_index": 8 }, { "op": "insert", "reference": null, "hypothesis": "शौक़", "reference_index": null, "hypothesis_index": 9 }, { "op": "substitute", "reference": "शौक", "hypothesis": "नहीं", "reference_index": 8, "hypothesis_index": 10 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.6722, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Neutral", "emotion_confidence": 0.27974438667297363, "duration_seconds": 1.7239999999999966, "mos": 2.8793, "audio_variant": "cleaned", "original_transcript_raw": "अगर इस दवा का टेस्ट हो जाता तो", "original_transcript": "अगर इस दवा का टेस्ट हो जाता तो", "retranscribed_transcript": "कि अगर इस दवा का टेस्ट हो जाता तो", "backend": "bodhan", "emotion_analyzed_seconds": 1.724, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-177", "energy": { "value": 0.640625, "bucket": "high" }, "audio_url": "audio/utterance-177.wav", "spectrogram_url": "spectrograms/utterance-177.png", "waveform": [ 0.46673, 0.30442, 1.06898, 1.0196, 1.09997, 1.0516, 1.09286, 1.07187, 1.04479, 1.03983, 1.11382, 1.03499, 1.08858, 1.0819, 0.86827, 0.58965, 0.51495, 0.55122, 0.99654, 0.98826, 1.02962, 1.11809, 1.0724, 1.03685, 1.07166, 1.01893, 0.48265, 0.66838, 0.64348, 0.79718, 0.8936, 0.92166, 0.98652, 1.0471, 1.04305, 1.06837, 1.01626, 1.02692, 0.62603, 0.21534, 0.1475, 0.10316, 0.02366, 0.01891, 0.02454, 0.19115, 1.04469, 1.00464, 1.0259, 1.05238, 1.01699, 0.80332, 0.70183, 0.88303, 1.04718, 1.02685, 1.11873, 1.11745, 1.09087, 1.06372, 1.09201, 1.03699, 1.01892, 0.55622, 0.1801, 0.10904, 0.11881, 0.11436, 0.13269, 0.58978, 1.02997, 1.02243, 0.96867, 1.0403, 0.70265, 0.20335, 0.06039, 0.03764, 0.03347, 0.01921, 0.01474, 0.00955, 0.00892, 0.12562, 0.43293, 1.05364, 1.04665, 1.05058, 1.0565, 1.06612, 1.03352, 1.04549, 1.01075, 1.05089, 0.88853, 0.65454, 0.50697, 0.40235, 0.24948, 0.23267, 0.20297, 0.02023, 0.0149, 0.01244, 0.01198, 0.22716, 0.11018, 0.04087, 0.02602, 0.12163, 0.27712, 0.48915, 0.64268, 0.82362, 0.95227, 0.99073, 0.95085, 0.45478, 0.58269, 0.72545, 1.01704, 1.03914, 1.05375, 1.07348, 1.07881, 1.03186, 1.04324, 1.02343, 0.87336, 0.22542, 0.11011, 0.03418, 0.02929, 0.15503, 0.24263, 1.02677, 1.05341, 1.05876, 1.039, 1.02724, 0.92197, 0.58504, 0.08138, 0.06426, 0.02586, 0.01703, 0.01858, 0.2401, 0.27092, 1.05973, 1.05731, 1.0542, 1.03761, 0.89283, 0.76512, 0.32492, 0.16379, 0.03106, 0.01764, 0.01693, 0.0153, 0.01585, 0.01127, 0.01163, 0.01038, 0.00835, 0.00566, 0.00244, 0.00153, 0.00157, 0.00107, 0.00108, 0.0007, 0.00118, 0.00277, 0.04573, 0.09457, 0.14366, 0.20116, 0.20566 ], "comparison": { "original": "अगर इस दवा का टेस्ट हो जाता तो", "retranscribed": "कि अगर इस दवा का टेस्ट हो जाता तो", "reference_tokens": [ "अगर", "इस", "दवा", "का", "टेस्ट", "हो", "जाता", "तो" ], "hypothesis_tokens": [ "कि", "अगर", "इस", "दवा", "का", "टेस्ट", "हो", "जाता", "तो" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 8, "reference_words": 8, "hypothesis_words": 9, "edits": 1 }, "wer": 0.125, "wer_percent": 12.5, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "कि", "reference_index": null, "hypothesis_index": 0 }, { "op": "equal", "reference": "अगर", "hypothesis": "अगर", "reference_index": 0, "hypothesis_index": 1 }, { "op": "equal", "reference": "इस", "hypothesis": "इस", "reference_index": 1, "hypothesis_index": 2 }, { "op": "equal", "reference": "दवा", "hypothesis": "दवा", "reference_index": 2, "hypothesis_index": 3 }, { "op": "equal", "reference": "का", "hypothesis": "का", "reference_index": 3, "hypothesis_index": 4 }, { "op": "equal", "reference": "टेस्ट", "hypothesis": "टेस्ट", "reference_index": 4, "hypothesis_index": 5 }, { "op": "equal", "reference": "हो", "hypothesis": "हो", "reference_index": 5, "hypothesis_index": 6 }, { "op": "equal", "reference": "जाता", "hypothesis": "जाता", "reference_index": 6, "hypothesis_index": 7 }, { "op": "equal", "reference": "तो", "hypothesis": "तो", "reference_index": 7, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz float32 WAV", "source_peak_abs": 1.11873, "audio_sample_format": "float32" }, { "language": "Hindi", "emotion": "Neutral", "emotion_confidence": 0.46722254157066345, "duration_seconds": 3.652000000000001, "mos": 3.5944, "audio_variant": "cleaned", "original_transcript_raw": "आप लोगों ने डिवाइड एंड रूल पॉलिसी तो हमें पहले ही सिखाई थी। ", "original_transcript": "आप लोगों ने डिवाइड एंड रूल पॉलिसी तो हमें पहले ही सिखाई थी।", "retranscribed_transcript": "आप लोगों ने डिवाइड एंड रूल पॉलिसी तो हमें पहले ही सिखाई थी", "backend": "bodhan", "emotion_analyzed_seconds": 3.652, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-178", "energy": { "value": 0.58984375, "bucket": "high" }, "audio_url": "audio/utterance-178.wav", "spectrogram_url": "spectrograms/utterance-178.png", "waveform": [ 0.06653, 0.02849, 0.11843, 0.39212, 0.16202, 0.16408, 0.2934, 0.61071, 0.37941, 0.36064, 0.41733, 0.4046, 0.18142, 0.09084, 0.31986, 0.44211, 0.29923, 0.3148, 0.32891, 0.18711, 0.18814, 0.28897, 0.32837, 0.40791, 0.4233, 0.39589, 0.402, 0.30932, 0.06651, 0.06517, 0.05018, 0.24623, 0.26517, 0.27926, 0.20086, 0.17405, 0.14775, 0.24684, 0.35596, 0.52011, 0.62319, 0.71653, 0.38253, 0.50972, 0.33552, 0.35241, 0.36589, 0.13141, 0.07862, 0.37953, 0.45907, 0.59827, 0.53508, 0.37699, 0.34202, 0.18054, 0.16177, 0.08476, 0.37449, 0.20266, 0.19848, 0.22035, 0.24402, 0.28645, 0.34205, 0.38333, 0.34111, 0.19221, 0.18012, 0.13126, 0.03884, 0.01408, 0.00839, 0.09661, 0.27659, 0.24521, 0.3623, 0.46541, 0.46866, 0.33982, 0.16358, 0.2698, 0.31549, 0.28779, 0.2653, 0.14707, 0.06877, 0.08014, 0.0776, 0.04258, 0.04585, 0.10218, 0.15635, 0.19682, 0.17943, 0.16143, 0.11325, 0.02744, 0.01531, 0.02197, 0.25501, 0.24116, 0.23343, 0.31097, 0.39185, 0.17709, 0.16393, 0.35318, 0.48537, 0.44895, 0.255, 0.21434, 0.2955, 0.53171, 0.51203, 0.51497, 0.29267, 0.0481, 0.00921, 0.00165, 0.21374, 0.45459, 0.41598, 0.41076, 0.33202, 0.31858, 0.23579, 0.15034, 0.11927, 0.2204, 0.39539, 0.4078, 0.41259, 0.28187, 0.23264, 0.1633, 0.13881, 0.07168, 0.05309, 0.06699, 0.07096, 0.05404, 0.04356, 0.12795, 0.1486, 0.04943, 0.02128, 0.0499, 0.1373, 0.03876, 0.0701, 0.127, 0.39936, 0.26785, 0.21284, 0.15802, 0.1299, 0.12779, 0.12401, 0.07109, 0.03059, 0.00244, 0.03695, 0.03546, 0.04153, 0.03846, 0.02927, 0.03046, 0.08383, 0.06436, 0.06673, 0.06554, 0.0596, 0.05203, 0.0255, 0.01504, 0.00895, 0.00784, 0.00679, 0.0095 ], "comparison": { "original": "आप लोगों ने डिवाइड एंड रूल पॉलिसी तो हमें पहले ही सिखाई थी।", "retranscribed": "आप लोगों ने डिवाइड एंड रूल पॉलिसी तो हमें पहले ही सिखाई थी", "reference_tokens": [ "आप", "लोगों", "ने", "डिवाइड", "एंड", "रूल", "पॉलिसी", "तो", "हमें", "पहले", "ही", "सिखाई", "थी" ], "hypothesis_tokens": [ "आप", "लोगों", "ने", "डिवाइड", "एंड", "रूल", "पॉलिसी", "तो", "हमें", "पहले", "ही", "सिखाई", "थी" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 13, "reference_words": 13, "hypothesis_words": 13, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "आप", "hypothesis": "आप", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "लोगों", "hypothesis": "लोगों", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "ने", "hypothesis": "ने", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "डिवाइड", "hypothesis": "डिवाइड", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "एंड", "hypothesis": "एंड", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "रूल", "hypothesis": "रूल", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "पॉलिसी", "hypothesis": "पॉलिसी", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "तो", "hypothesis": "तो", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "हमें", "hypothesis": "हमें", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "पहले", "hypothesis": "पहले", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "ही", "hypothesis": "ही", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "सिखाई", "hypothesis": "सिखाई", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "थी", "hypothesis": "थी", "reference_index": 12, "hypothesis_index": 12 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.71653, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Neutral", "emotion_confidence": 0.3798994719982147, "duration_seconds": 1.774000000000001, "mos": 3.1649, "audio_variant": "cleaned", "original_transcript_raw": "वो चकले के रिटे मेरी हेरोइनों से", "original_transcript": "वो चकले के रिटे मेरी हेरोइनों से", "retranscribed_transcript": "वो चकले की रेंटे मेरी हीरोइन हो सकती है", "backend": "bodhan", "emotion_analyzed_seconds": 1.774, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-179", "energy": { "value": 0.59375, "bucket": "high" }, "audio_url": "audio/utterance-179.wav", "spectrogram_url": "spectrograms/utterance-179.png", "waveform": [ 0.00519, 0.00384, 0.003, 0.00174, 0.00059, 0.00052, 0.01902, 0.06323, 0.06381, 0.07079, 0.06232, 0.06347, 0.04798, 0.0353, 0.03112, 0.03222, 0.02927, 0.03155, 0.06221, 0.12327, 0.1593, 0.18837, 0.30956, 0.28953, 0.3631, 0.45108, 0.42949, 0.44468, 0.41578, 0.41466, 0.34435, 0.31504, 0.17577, 0.07909, 0.05942, 0.03624, 0.01926, 0.04586, 0.09321, 0.10199, 0.14734, 0.14705, 0.20541, 0.35467, 0.34675, 0.39604, 0.35141, 0.21596, 0.09976, 0.07922, 0.05303, 0.02655, 0.076, 0.04372, 0.26285, 0.34637, 0.36275, 0.29684, 0.22441, 0.30076, 0.38056, 0.36612, 0.32973, 0.21259, 0.16184, 0.09034, 0.07123, 0.05209, 0.06709, 0.11931, 0.27291, 0.33019, 0.38104, 0.251, 0.10211, 0.11063, 0.25937, 0.30867, 0.31883, 0.34295, 0.26176, 0.20219, 0.18762, 0.18839, 0.16951, 0.16272, 0.15101, 0.10963, 0.07107, 0.06892, 0.15161, 0.25664, 0.17314, 0.11522, 0.08179, 0.0808, 0.10102, 0.15375, 0.25219, 0.27523, 0.27542, 0.28014, 0.26113, 0.16158, 0.05856, 0.08357, 0.11205, 0.1002, 0.07091, 0.0733, 0.06412, 0.04373, 0.03829, 0.03656, 0.03427, 0.0365, 0.05855, 0.14545, 0.15866, 0.18217, 0.13357, 0.09012, 0.12507, 0.20846, 0.19718, 0.20658, 0.19982, 0.23643, 0.2288, 0.22781, 0.21222, 0.18739, 0.1892, 0.14961, 0.10348, 0.09591, 0.09739, 0.07846, 0.1257, 0.12929, 0.10418, 0.08663, 0.08722, 0.09223, 0.09857, 0.09052, 0.07831, 0.0573, 0.03917, 0.04288, 0.03904, 0.03382, 0.03547, 0.03745, 0.03429, 0.03027, 0.01133, 0.01325, 0.02505, 0.02164, 0.02193, 0.01382, 0.00318, 0.00137, 0.00092, 0.00042, 0.00023, 0.00025, 0.00016, 0.00013, 0.00012, 9e-05, 9e-05, 7e-05, 0.0001, 0.00157, 0.00269, 0.00436, 0.01587, 0.01117 ], "comparison": { "original": "वो चकले के रिटे मेरी हेरोइनों से", "retranscribed": "वो चकले की रेंटे मेरी हीरोइन हो सकती है", "reference_tokens": [ "वो", "चकले", "के", "रिटे", "मेरी", "हेरोइनों", "से" ], "hypothesis_tokens": [ "वो", "चकले", "की", "रेंटे", "मेरी", "हीरोइन", "हो", "सकती", "है" ], "counts": { "substitutions": 4, "deletions": 0, "insertions": 2, "hits": 3, "reference_words": 7, "hypothesis_words": 9, "edits": 6 }, "wer": 0.8571428571428571, "wer_percent": 85.71428571428571, "alignment": [ { "op": "equal", "reference": "वो", "hypothesis": "वो", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "चकले", "hypothesis": "चकले", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "के", "hypothesis": "की", "reference_index": 2, "hypothesis_index": 2 }, { "op": "substitute", "reference": "रिटे", "hypothesis": "रेंटे", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "मेरी", "hypothesis": "मेरी", "reference_index": 4, "hypothesis_index": 4 }, { "op": "insert", "reference": null, "hypothesis": "हीरोइन", "reference_index": null, "hypothesis_index": 5 }, { "op": "insert", "reference": null, "hypothesis": "हो", "reference_index": null, "hypothesis_index": 6 }, { "op": "substitute", "reference": "हेरोइनों", "hypothesis": "सकती", "reference_index": 5, "hypothesis_index": 7 }, { "op": "substitute", "reference": "से", "hypothesis": "है", "reference_index": 6, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.45108, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Sad", "emotion_confidence": 0.4176923930644989, "duration_seconds": 5.256000000000029, "mos": 3.2494, "audio_variant": "cleaned", "original_transcript_raw": "ये सब कुछ उस जायदाद और दौलत की वजह से हो रहा है जो मुझे अभी अभी मिली है। ", "original_transcript": "ये सब कुछ उस जायदाद और दौलत की वजह से हो रहा है जो मुझे अभी अभी मिली है।", "retranscribed_transcript": "ये सब कुछ उस जायदाद और दौलत की वजह से हो रहा है जो मुझे अभी अभी मिली है", "backend": "bodhan", "emotion_analyzed_seconds": 5.256, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-180", "energy": { "value": 0.50390625, "bucket": "low" }, "audio_url": "audio/utterance-180.wav", "spectrogram_url": "spectrograms/utterance-180.png", "waveform": [ 0.00342, 0.09359, 0.12946, 0.28148, 0.23725, 0.04855, 0.05486, 0.38208, 0.51737, 0.42466, 0.06066, 0.00283, 0.0011, 0.34049, 0.51676, 0.52166, 0.05152, 0.2509, 0.23024, 0.2688, 0.211, 0.07671, 0.03646, 0.05257, 0.05444, 0.05052, 0.01301, 0.0018, 0.00114, 0.00076, 0.00055, 0.00056, 0.0003, 0.00044, 0.00028, 0.00032, 0.0004, 0.00033, 0.00027, 0.00026, 0.00029, 0.00043, 0.00042, 0.00041, 0.00053, 0.00067, 0.00063, 0.0707, 0.20374, 0.38306, 0.4585, 0.53294, 0.37215, 0.43073, 0.38852, 0.18532, 0.56414, 0.34102, 0.39941, 0.41275, 0.23012, 0.3413, 0.39725, 0.19035, 0.08233, 0.0039, 0.51158, 0.47299, 0.27866, 0.23363, 0.1982, 0.32291, 0.29511, 0.30391, 0.00707, 0.01129, 0.0506, 0.38634, 0.4169, 0.15741, 0.38313, 0.36667, 0.22714, 0.22213, 0.28751, 0.30476, 0.21092, 0.09679, 0.03936, 0.06303, 0.36529, 0.38812, 0.29709, 0.25355, 0.25023, 0.27789, 0.29095, 0.26219, 0.27086, 0.2409, 0.24254, 0.2541, 0.21819, 0.15731, 0.1508, 0.09144, 0.07762, 0.03316, 0.00111, 0.001, 0.00122, 0.00093, 0.00891, 0.01698, 0.02252, 0.01571, 0.02259, 0.02237, 0.01989, 0.01624, 0.01661, 0.01379, 0.00997, 0.00725, 0.00669, 0.004, 0.00325, 0.00205, 0.00139, 0.00125, 0.00099, 0.00104, 0.00115, 0.00117, 0.1846, 0.36331, 0.3568, 0.24598, 0.37688, 0.44459, 0.2468, 0.261, 0.22038, 0.20925, 0.32738, 0.34628, 0.46577, 0.14723, 0.08662, 0.13198, 0.17478, 0.35411, 0.54945, 0.19038, 0.09517, 0.31398, 0.34591, 0.38409, 0.38996, 0.35199, 0.26187, 0.21892, 0.23465, 0.2873, 0.28516, 0.18921, 0.16076, 0.17104, 0.21892, 0.11992, 0.00734, 0.00125, 0.00051, 0.00045, 0.00024, 0.00017, 2e-05, 5e-05, 0.00213, 0.0113 ], "comparison": { "original": "ये सब कुछ उस जायदाद और दौलत की वजह से हो रहा है जो मुझे अभी अभी मिली है।", "retranscribed": "ये सब कुछ उस जायदाद और दौलत की वजह से हो रहा है जो मुझे अभी अभी मिली है", "reference_tokens": [ "ये", "सब", "कुछ", "उस", "जायदाद", "और", "दौलत", "की", "वजह", "से", "हो", "रहा", "है", "जो", "मुझे", "अभी", "अभी", "मिली", "है" ], "hypothesis_tokens": [ "ये", "सब", "कुछ", "उस", "जायदाद", "और", "दौलत", "की", "वजह", "से", "हो", "रहा", "है", "जो", "मुझे", "अभी", "अभी", "मिली", "है" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 19, "reference_words": 19, "hypothesis_words": 19, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "ये", "hypothesis": "ये", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "सब", "hypothesis": "सब", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "कुछ", "hypothesis": "कुछ", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "उस", "hypothesis": "उस", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "जायदाद", "hypothesis": "जायदाद", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "और", "hypothesis": "और", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "दौलत", "hypothesis": "दौलत", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "की", "hypothesis": "की", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "वजह", "hypothesis": "वजह", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "से", "hypothesis": "से", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "हो", "hypothesis": "हो", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "रहा", "hypothesis": "रहा", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "जो", "hypothesis": "जो", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "मुझे", "hypothesis": "मुझे", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "अभी", "hypothesis": "अभी", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "अभी", "hypothesis": "अभी", "reference_index": 16, "hypothesis_index": 16 }, { "op": "equal", "reference": "मिली", "hypothesis": "मिली", "reference_index": 17, "hypothesis_index": 17 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 18, "hypothesis_index": 18 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.56414, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Sad", "emotion_confidence": 0.7448745965957642, "duration_seconds": 8.396, "mos": 3.678, "audio_variant": "cleaned", "original_transcript_raw": "बोली शिभा के बिहारीलालिकी शीराधारानी सरकार की", "original_transcript": "बोली शिभा के बिहारीलालिकी शीराधारानी सरकार की", "retranscribed_transcript": "बोले शिवां के बिहारी लाल की श्री राधा रानी सरकार की", "backend": "bodhan", "emotion_analyzed_seconds": 8.396, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-181", "energy": { "value": 0.3515625, "bucket": "low" }, "audio_url": "audio/utterance-181.wav", "spectrogram_url": "spectrograms/utterance-181.png", "waveform": [ 0.19356, 0.27366, 0.29919, 0.42847, 0.4133, 0.28465, 0.14951, 0.149, 0.35186, 0.31956, 0.39602, 0.56233, 0.43933, 0.33752, 0.29401, 0.21019, 0.1669, 0.33353, 0.36547, 0.36505, 0.33771, 0.30544, 0.27965, 0.27525, 0.27259, 0.29381, 0.1826, 0.29342, 0.23053, 0.27569, 0.36175, 0.3645, 0.38479, 0.34867, 0.32849, 0.41946, 0.46581, 0.44395, 0.39559, 0.41479, 0.38924, 0.36083, 0.36738, 0.34209, 0.29026, 0.26399, 0.23699, 0.21933, 0.19375, 0.17881, 0.26168, 0.27727, 0.26144, 0.00712, 0.00344, 0.11201, 0.30774, 0.30719, 0.28135, 0.22807, 0.18291, 0.14572, 0.10739, 0.07861, 0.04927, 0.02683, 0.00369, 0.00254, 0.00122, 0.00054, 0.00022, 3e-05, 2e-05, 2e-05, 2e-05, 2e-05, 0.00043, 0.0046, 0.00414, 0.03374, 0.06938, 0.06806, 0.06602, 0.08225, 0.08236, 0.08517, 0.09928, 0.14207, 0.10512, 0.089, 0.41674, 0.41289, 0.2611, 0.33932, 0.3251, 0.31453, 0.25087, 0.21529, 0.29507, 0.35, 0.34225, 0.32249, 0.29653, 0.29982, 0.27843, 0.29381, 0.25439, 0.26502, 0.25744, 0.24463, 0.23232, 0.20594, 0.19806, 0.20488, 0.20057, 0.18693, 0.15503, 0.13694, 0.11814, 0.11655, 0.09554, 0.07967, 0.04212, 0.01492, 0.01796, 0.1582, 0.26713, 0.26434, 0.22886, 0.00296, 0.1128, 0.26954, 0.26295, 0.22217, 0.18403, 0.14004, 0.10509, 0.11893, 0.10015, 0.09942, 0.09977, 0.09784, 0.10587, 0.0915, 0.09635, 0.10379, 0.13643, 0.12786, 0.11594, 0.1064, 0.00394, 0.00154, 0.07377, 0.04116, 0.11997, 0.11754, 0.10052, 0.06895, 0.05547, 0.03487, 0.02124, 0.00379, 0.00033, 3e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 2e-05, 0.00084, 0.01563 ], "comparison": { "original": "बोली शिभा के बिहारीलालिकी शीराधारानी सरकार की", "retranscribed": "बोले शिवां के बिहारी लाल की श्री राधा रानी सरकार की", "reference_tokens": [ "बोली", "शिभा", "के", "बिहारीलालिकी", "शीराधारानी", "सरकार", "की" ], "hypothesis_tokens": [ "बोले", "शिवां", "के", "बिहारी", "लाल", "की", "श्री", "राधा", "रानी", "सरकार", "की" ], "counts": { "substitutions": 4, "deletions": 0, "insertions": 4, "hits": 3, "reference_words": 7, "hypothesis_words": 11, "edits": 8 }, "wer": 1.1428571428571428, "wer_percent": 114.28571428571428, "alignment": [ { "op": "substitute", "reference": "बोली", "hypothesis": "बोले", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "शिभा", "hypothesis": "शिवां", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "के", "hypothesis": "के", "reference_index": 2, "hypothesis_index": 2 }, { "op": "insert", "reference": null, "hypothesis": "बिहारी", "reference_index": null, "hypothesis_index": 3 }, { "op": "insert", "reference": null, "hypothesis": "लाल", "reference_index": null, "hypothesis_index": 4 }, { "op": "insert", "reference": null, "hypothesis": "की", "reference_index": null, "hypothesis_index": 5 }, { "op": "insert", "reference": null, "hypothesis": "श्री", "reference_index": null, "hypothesis_index": 6 }, { "op": "substitute", "reference": "बिहारीलालिकी", "hypothesis": "राधा", "reference_index": 3, "hypothesis_index": 7 }, { "op": "substitute", "reference": "शीराधारानी", "hypothesis": "रानी", "reference_index": 4, "hypothesis_index": 8 }, { "op": "equal", "reference": "सरकार", "hypothesis": "सरकार", "reference_index": 5, "hypothesis_index": 9 }, { "op": "equal", "reference": "की", "hypothesis": "की", "reference_index": 6, "hypothesis_index": 10 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.56233, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Sad", "emotion_confidence": 0.3797280788421631, "duration_seconds": 2.0649999999999977, "mos": 3.5233, "audio_variant": "cleaned", "original_transcript_raw": "आज की बात तो हमेशा के लिए मेरी वो चौकी बस", "original_transcript": "आज की बात तो हमेशा के लिए मेरी वो चौकी बस", "retranscribed_transcript": "आज के बाद तुम हमेशा के लिए मेरी वजहों की वजह", "backend": "bodhan", "emotion_analyzed_seconds": 2.065, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-182", "energy": { "value": 0.5078125, "bucket": "low" }, "audio_url": "audio/utterance-182.wav", "spectrogram_url": "spectrograms/utterance-182.png", "waveform": [ 0.11348, 0.07812, 0.0723, 0.13473, 0.23656, 0.18984, 0.2112, 0.23118, 0.25657, 0.29363, 0.30532, 0.29173, 0.25814, 0.17225, 0.05918, 0.06808, 0.08114, 0.10588, 0.16595, 0.12666, 0.07079, 0.05176, 0.05952, 0.08263, 0.06927, 0.06928, 0.02507, 0.12408, 0.13842, 0.08913, 0.03658, 0.04584, 0.1859, 0.16916, 0.38457, 0.42192, 0.36911, 0.39059, 0.47477, 0.41287, 0.43074, 0.28439, 0.08739, 0.02462, 0.00899, 0.00622, 0.00478, 0.00348, 0.00136, 0.00139, 0.00292, 0.19908, 0.26284, 0.45089, 0.4223, 0.39952, 0.33581, 0.28312, 0.22, 0.16461, 0.15733, 0.09041, 0.0687, 0.0525, 0.04217, 0.03282, 0.03211, 0.02844, 0.02471, 0.02127, 0.0261, 0.02508, 0.03363, 0.02952, 0.02079, 0.02104, 0.0111, 0.14817, 0.24949, 0.24878, 0.28724, 0.24566, 0.23582, 0.24184, 0.23765, 0.20009, 0.11737, 0.08914, 0.08117, 0.10865, 0.20012, 0.17747, 0.25223, 0.20053, 0.11113, 0.07129, 0.2244, 0.30998, 0.34934, 0.30866, 0.27285, 0.11128, 0.0537, 0.07367, 0.20375, 0.28464, 0.33018, 0.39692, 0.22112, 0.22015, 0.21515, 0.22199, 0.24892, 0.28485, 0.29795, 0.30356, 0.29509, 0.22984, 0.165, 0.14275, 0.20353, 0.20328, 0.25071, 0.27278, 0.2494, 0.23054, 0.26109, 0.17881, 0.06816, 0.10307, 0.20066, 0.23438, 0.27818, 0.29058, 0.23933, 0.19605, 0.19771, 0.19052, 0.16763, 0.15729, 0.17929, 0.15462, 0.07262, 0.02206, 0.07415, 0.11679, 0.18586, 0.1063, 0.04638, 0.20395, 0.24215, 0.18457, 0.16974, 0.16187, 0.11509, 0.08258, 0.06512, 0.0311, 0.0072, 0.01262, 0.02542, 0.02422, 0.02668, 0.03103, 0.18113, 0.19032, 0.16226, 0.16032, 0.15553, 0.13683, 0.12818, 0.11623, 0.08062, 0.05998, 0.0648, 0.06912, 0.05634, 0.08072, 0.14881, 0.213 ], "comparison": { "original": "आज की बात तो हमेशा के लिए मेरी वो चौकी बस", "retranscribed": "आज के बाद तुम हमेशा के लिए मेरी वजहों की वजह", "reference_tokens": [ "आज", "की", "बात", "तो", "हमेशा", "के", "लिए", "मेरी", "वो", "चौकी", "बस" ], "hypothesis_tokens": [ "आज", "के", "बाद", "तुम", "हमेशा", "के", "लिए", "मेरी", "वजहों", "की", "वजह" ], "counts": { "substitutions": 6, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 11, "hypothesis_words": 11, "edits": 6 }, "wer": 0.5454545454545454, "wer_percent": 54.54545454545454, "alignment": [ { "op": "equal", "reference": "आज", "hypothesis": "आज", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "की", "hypothesis": "के", "reference_index": 1, "hypothesis_index": 1 }, { "op": "substitute", "reference": "बात", "hypothesis": "बाद", "reference_index": 2, "hypothesis_index": 2 }, { "op": "substitute", "reference": "तो", "hypothesis": "तुम", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "हमेशा", "hypothesis": "हमेशा", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "के", "hypothesis": "के", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "लिए", "hypothesis": "लिए", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "मेरी", "hypothesis": "मेरी", "reference_index": 7, "hypothesis_index": 7 }, { "op": "substitute", "reference": "वो", "hypothesis": "वजहों", "reference_index": 8, "hypothesis_index": 8 }, { "op": "substitute", "reference": "चौकी", "hypothesis": "की", "reference_index": 9, "hypothesis_index": 9 }, { "op": "substitute", "reference": "बस", "hypothesis": "वजह", "reference_index": 10, "hypothesis_index": 10 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.47477, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Sad", "emotion_confidence": 0.441703200340271, "duration_seconds": 2.372, "mos": 3.1419, "audio_variant": "cleaned", "original_transcript_raw": "हमारे रिश्ते ने पहले भी छूट की कीमत चुकाई। ", "original_transcript": "हमारे रिश्ते ने पहले भी छूट की कीमत चुकाई।", "retranscribed_transcript": "हमारे रिश्ते ने पहले भी छूट की कीमत चुकाई है", "backend": "bodhan", "emotion_analyzed_seconds": 2.372, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-183", "energy": { "value": 0.55078125, "bucket": "medium" }, "audio_url": "audio/utterance-183.wav", "spectrogram_url": "spectrograms/utterance-183.png", "waveform": [ 0.18549, 0.15903, 0.19088, 0.29596, 0.30015, 0.2114, 0.2057, 0.21006, 0.25112, 0.32456, 0.29787, 0.30478, 0.30627, 0.29173, 0.24884, 0.25613, 0.15394, 0.09938, 0.10007, 0.14733, 0.1334, 0.15108, 0.16733, 0.16374, 0.10883, 0.0716, 0.05043, 0.04526, 0.05164, 0.19119, 0.2307, 0.15577, 0.08512, 0.05899, 0.07466, 0.06513, 0.05943, 0.07126, 0.06133, 0.02207, 0.00333, 0.00021, 0.0001, 0.0019, 0.04538, 0.27942, 0.23767, 0.22868, 0.27871, 0.27854, 0.16907, 0.18317, 0.1848, 0.19547, 0.22922, 0.22743, 0.21519, 0.1647, 0.05482, 0.01073, 0.00053, 0.00017, 0.00013, 0.00494, 0.23742, 0.28179, 0.31924, 0.27971, 0.26578, 0.23363, 0.20753, 0.12805, 0.12475, 0.13397, 0.13697, 0.20866, 0.21983, 0.21272, 0.19122, 0.17984, 0.11383, 0.03734, 0.00621, 0.00044, 0.00789, 0.02826, 0.20455, 0.24683, 0.22461, 0.20854, 0.18738, 0.17708, 0.1216, 0.09305, 0.01773, 0.00147, 0.01134, 0.04852, 0.07824, 0.05868, 0.06063, 0.07169, 0.07872, 0.06475, 0.027, 0.20716, 0.20997, 0.15396, 0.12788, 0.03438, 0.00931, 0.00113, 0.00452, 0.00056, 0.00101, 0.03032, 0.03315, 0.20029, 0.19891, 0.18684, 0.16289, 0.09326, 0.02638, 0.00342, 0.00907, 0.02003, 0.01897, 0.113, 0.18272, 0.20692, 0.18996, 0.1577, 0.14144, 0.12922, 0.12377, 0.12212, 0.12395, 0.19851, 0.2162, 0.21896, 0.15428, 0.0455, 0.00703, 0.00025, 0.00324, 0.06297, 0.07194, 0.02993, 0.11376, 0.2097, 0.17508, 0.07722, 0.00494, 0.00079, 0.01063, 0.14022, 0.09563, 0.13594, 0.11738, 0.10336, 0.11494, 0.08555, 0.08811, 0.08631, 0.04563, 0.02415, 0.01221, 0.01793, 0.01535, 0.02281, 0.01835, 0.01808, 0.02053, 0.01902, 0.02082, 0.03314, 0.02902, 0.0204, 0.02971, 0.03282 ], "comparison": { "original": "हमारे रिश्ते ने पहले भी छूट की कीमत चुकाई।", "retranscribed": "हमारे रिश्ते ने पहले भी छूट की कीमत चुकाई है", "reference_tokens": [ "हमारे", "रिश्ते", "ने", "पहले", "भी", "छूट", "की", "कीमत", "चुकाई" ], "hypothesis_tokens": [ "हमारे", "रिश्ते", "ने", "पहले", "भी", "छूट", "की", "कीमत", "चुकाई", "है" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 1, "hits": 9, "reference_words": 9, "hypothesis_words": 10, "edits": 1 }, "wer": 0.1111111111111111, "wer_percent": 11.11111111111111, "alignment": [ { "op": "equal", "reference": "हमारे", "hypothesis": "हमारे", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "रिश्ते", "hypothesis": "रिश्ते", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "ने", "hypothesis": "ने", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "पहले", "hypothesis": "पहले", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "भी", "hypothesis": "भी", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "छूट", "hypothesis": "छूट", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "की", "hypothesis": "की", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "कीमत", "hypothesis": "कीमत", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "चुकाई", "hypothesis": "चुकाई", "reference_index": 8, "hypothesis_index": 8 }, { "op": "insert", "reference": null, "hypothesis": "है", "reference_index": null, "hypothesis_index": 9 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.32456, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Sad", "emotion_confidence": 0.3319978713989258, "duration_seconds": 1.2290000000000134, "mos": 3.0718, "audio_variant": "cleaned", "original_transcript_raw": "चलो तमानी दी के बाद। ", "original_transcript": "चलो तमानी दी के बाद।", "retranscribed_transcript": "चलो तुम्हारी दी के पास", "backend": "bodhan", "emotion_analyzed_seconds": 1.229, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-184", "energy": { "value": 0.54296875, "bucket": "medium" }, "audio_url": "audio/utterance-184.wav", "spectrogram_url": "spectrograms/utterance-184.png", "waveform": [ 0.11041, 0.09492, 0.11983, 0.1943, 0.19675, 0.23625, 0.19838, 0.24392, 0.23663, 0.19578, 0.16408, 0.1574, 0.09912, 0.10971, 0.13344, 0.14318, 0.19272, 0.2265, 0.20693, 0.18265, 0.16924, 0.19665, 0.20207, 0.20419, 0.2054, 0.1809, 0.15613, 0.15548, 0.1129, 0.07792, 0.0724, 0.02766, 0.00963, 0.00356, 0.00059, 0.00046, 0.00024, 0.00013, 0.00012, 0.00011, 0.00011, 0.00012, 0.00011, 9e-05, 9e-05, 8e-05, 8e-05, 6e-05, 6e-05, 6e-05, 6e-05, 6e-05, 6e-05, 5e-05, 5e-05, 4e-05, 4e-05, 4e-05, 4e-05, 3e-05, 3e-05, 4e-05, 2e-05, 2e-05, 3e-05, 3e-05, 2e-05, 3e-05, 2e-05, 3e-05, 3e-05, 3e-05, 4e-05, 0.00011, 0.00023, 0.0007, 0.00546, 0.1542, 0.06734, 0.07235, 0.07734, 0.17186, 0.15201, 0.12391, 0.07535, 0.05925, 0.06294, 0.05141, 0.05557, 0.11269, 0.0837, 0.24355, 0.30395, 0.27802, 0.27293, 0.20055, 0.2236, 0.24037, 0.23819, 0.24288, 0.23394, 0.18829, 0.1429, 0.1682, 0.17593, 0.16493, 0.15236, 0.15233, 0.15399, 0.15134, 0.15248, 0.15573, 0.15146, 0.13091, 0.08959, 0.08383, 0.06453, 0.04815, 0.03708, 0.01992, 0.01317, 0.05154, 0.09524, 0.07357, 0.21303, 0.17652, 0.16178, 0.15184, 0.14444, 0.13705, 0.14779, 0.14955, 0.14595, 0.14282, 0.11771, 0.07208, 0.06086, 0.02938, 0.01987, 0.01334, 0.01825, 0.03168, 0.03095, 0.02859, 0.06618, 0.0569, 0.1163, 0.17712, 0.15883, 0.16354, 0.16536, 0.18236, 0.09995, 0.07689, 0.05297, 0.03421, 0.02614, 0.01963, 0.02602, 0.02969, 0.06218, 0.08466, 0.25127, 0.24045, 0.19296, 0.14465, 0.15315, 0.22045, 0.16022, 0.11854, 0.14238, 0.10147, 0.13584, 0.13178, 0.1013, 0.12037, 0.08078, 0.07779, 0.1079, 0.05639 ], "comparison": { "original": "चलो तमानी दी के बाद।", "retranscribed": "चलो तुम्हारी दी के पास", "reference_tokens": [ "चलो", "तमानी", "दी", "के", "बाद" ], "hypothesis_tokens": [ "चलो", "तुम्हारी", "दी", "के", "पास" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 3, "reference_words": 5, "hypothesis_words": 5, "edits": 2 }, "wer": 0.4, "wer_percent": 40.0, "alignment": [ { "op": "equal", "reference": "चलो", "hypothesis": "चलो", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "तमानी", "hypothesis": "तुम्हारी", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "दी", "hypothesis": "दी", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "के", "hypothesis": "के", "reference_index": 3, "hypothesis_index": 3 }, { "op": "substitute", "reference": "बाद", "hypothesis": "पास", "reference_index": 4, "hypothesis_index": 4 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.30395, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Sad", "emotion_confidence": 0.27962926030158997, "duration_seconds": 1.8939999999999912, "mos": 3.1661, "audio_variant": "original", "original_transcript_raw": "और मैं हार कर वापस नहीं जाना चाहती थी। ", "original_transcript": "और मैं हार कर वापस नहीं जाना चाहती थी।", "retranscribed_transcript": "और मैं हार कर वापस नहीं जाना चाहती थी", "backend": "bodhan", "emotion_analyzed_seconds": 1.894, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-185", "energy": { "value": 0.5625, "bucket": "medium" }, "audio_url": "audio/utterance-185.wav", "spectrogram_url": "spectrograms/utterance-185.png", "waveform": [ 0.04224, 0.0452, 0.2259, 0.33185, 0.35683, 0.37697, 0.36465, 0.36713, 0.31226, 0.34501, 0.29269, 0.27935, 0.25949, 0.27675, 0.27956, 0.27054, 0.26557, 0.26969, 0.27134, 0.31405, 0.33106, 0.29555, 0.29766, 0.32066, 0.31324, 0.29767, 0.28058, 0.26515, 0.29176, 0.3317, 0.31183, 0.25066, 0.24427, 0.31594, 0.30979, 0.31809, 0.37802, 0.34935, 0.34592, 0.39278, 0.34717, 0.32101, 0.32083, 0.2534, 0.24348, 0.2356, 0.22906, 0.11141, 0.02534, 0.0191, 0.0375, 0.03217, 0.37138, 0.24043, 0.26369, 0.34305, 0.33871, 0.32589, 0.26432, 0.24634, 0.23836, 0.21393, 0.2038, 0.22001, 0.28434, 0.2899, 0.28627, 0.35109, 0.377, 0.36727, 0.35336, 0.35998, 0.23596, 0.12097, 0.03398, 0.0396, 0.02285, 0.02272, 0.02358, 0.25781, 0.17329, 0.28689, 0.27895, 0.25612, 0.21907, 0.19757, 0.31468, 0.27201, 0.22002, 0.20415, 0.11993, 0.0343, 0.12623, 0.21606, 0.24734, 0.24103, 0.23768, 0.23233, 0.27174, 0.2881, 0.27798, 0.27148, 0.27922, 0.27415, 0.25712, 0.2713, 0.25886, 0.25375, 0.25802, 0.25819, 0.255, 0.2388, 0.24046, 0.22999, 0.22588, 0.2398, 0.29616, 0.23608, 0.27351, 0.27186, 0.24793, 0.24815, 0.25349, 0.24487, 0.219, 0.20591, 0.22547, 0.19143, 0.2016, 0.18226, 0.19757, 0.19791, 0.20289, 0.21523, 0.19921, 0.20567, 0.23989, 0.21761, 0.21777, 0.19315, 0.17885, 0.0684, 0.0652, 0.25295, 0.30864, 0.24225, 0.09277, 0.22241, 0.25114, 0.26851, 0.22356, 0.25901, 0.21077, 0.18486, 0.18887, 0.12213, 0.03339, 0.02234, 0.01529, 0.01813, 0.01954, 0.18204, 0.11347, 0.12423, 0.19871, 0.21217, 0.2146, 0.18999, 0.10391, 0.03961, 0.03349, 0.02215, 0.02723, 0.04191, 0.08243, 0.13152, 0.06089, 0.05498, 0.05467, 0.04856 ], "comparison": { "original": "और मैं हार कर वापस नहीं जाना चाहती थी।", "retranscribed": "और मैं हार कर वापस नहीं जाना चाहती थी", "reference_tokens": [ "और", "मैं", "हार", "कर", "वापस", "नहीं", "जाना", "चाहती", "थी" ], "hypothesis_tokens": [ "और", "मैं", "हार", "कर", "वापस", "नहीं", "जाना", "चाहती", "थी" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 9, "reference_words": 9, "hypothesis_words": 9, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "और", "hypothesis": "और", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "मैं", "hypothesis": "मैं", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "हार", "hypothesis": "हार", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "कर", "hypothesis": "कर", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "वापस", "hypothesis": "वापस", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "नहीं", "hypothesis": "नहीं", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "जाना", "hypothesis": "जाना", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "चाहती", "hypothesis": "चाहती", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "थी", "hypothesis": "थी", "reference_index": 8, "hypothesis_index": 8 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.39278, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Sad", "emotion_confidence": 0.41408294439315796, "duration_seconds": 1.450000000000017, "mos": 3.302, "audio_variant": "cleaned", "original_transcript_raw": "तो लड़की के बारे में सोच", "original_transcript": "तो लड़की के बारे में सोच", "retranscribed_transcript": "बेटा लड़की के बारे में सोच", "backend": "bodhan", "emotion_analyzed_seconds": 1.45, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-186", "energy": { "value": 0.59765625, "bucket": "high" }, "audio_url": "audio/utterance-186.wav", "spectrogram_url": "spectrograms/utterance-186.png", "waveform": [ 0.21893, 0.066, 0.11617, 0.16046, 0.12966, 0.11316, 0.05782, 0.01772, 0.00617, 0.00293, 0.00181, 0.00546, 0.12545, 0.08183, 0.04182, 0.22141, 0.34427, 0.37378, 0.38641, 0.44828, 0.46338, 0.39397, 0.28279, 0.23604, 0.22995, 0.28259, 0.26683, 0.28987, 0.28518, 0.31067, 0.38462, 0.41766, 0.41635, 0.37553, 0.38515, 0.37396, 0.36216, 0.32864, 0.28454, 0.24388, 0.15332, 0.09906, 0.10645, 0.10791, 0.07878, 0.02091, 0.01462, 0.00386, 0.00284, 0.00184, 0.00137, 0.00075, 0.00112, 0.00144, 0.10364, 0.05935, 0.03078, 0.02843, 0.04803, 0.40601, 0.45536, 0.44952, 0.41722, 0.37655, 0.27387, 0.14268, 0.05753, 0.01654, 0.0034, 0.00247, 0.00135, 0.00111, 0.06401, 0.05054, 0.07864, 0.04706, 0.02194, 0.03054, 0.31908, 0.36767, 0.49318, 0.53436, 0.48326, 0.12592, 0.12262, 0.08169, 0.06002, 0.04027, 0.03035, 0.02679, 0.12016, 0.20205, 0.20295, 0.2035, 0.22843, 0.23153, 0.271, 0.26867, 0.22819, 0.22427, 0.29382, 0.29192, 0.25715, 0.11257, 0.11994, 0.0999, 0.16054, 0.26791, 0.37466, 0.37192, 0.39302, 0.43532, 0.43566, 0.44062, 0.36072, 0.2382, 0.23951, 0.24892, 0.24514, 0.24589, 0.25979, 0.32163, 0.4889, 0.5301, 0.54542, 0.54255, 0.51354, 0.41902, 0.26859, 0.1586, 0.10351, 0.06428, 0.03882, 0.03365, 0.02647, 0.03356, 0.04424, 0.05028, 0.05614, 0.06159, 0.04935, 0.04177, 0.03374, 0.36169, 0.42407, 0.4027, 0.39554, 0.39018, 0.40503, 0.40108, 0.3048, 0.2732, 0.23052, 0.18986, 0.1512, 0.12596, 0.05481, 0.01449, 0.00575, 0.00368, 0.00169, 0.00128, 0.00078, 0.011, 0.02064, 0.04948, 0.0608, 0.07288, 0.04354, 0.03512, 0.02244, 0.01195, 0.00725, 0.00544, 0.00966, 0.01675, 0.02877, 0.04567, 0.04257, 0.06593 ], "comparison": { "original": "तो लड़की के बारे में सोच", "retranscribed": "बेटा लड़की के बारे में सोच", "reference_tokens": [ "तो", "लड़की", "के", "बारे", "में", "सोच" ], "hypothesis_tokens": [ "बेटा", "लड़की", "के", "बारे", "में", "सोच" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 0, "hits": 5, "reference_words": 6, "hypothesis_words": 6, "edits": 1 }, "wer": 0.16666666666666666, "wer_percent": 16.666666666666664, "alignment": [ { "op": "substitute", "reference": "तो", "hypothesis": "बेटा", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "लड़की", "hypothesis": "लड़की", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "के", "hypothesis": "के", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "बारे", "hypothesis": "बारे", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "में", "hypothesis": "में", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "सोच", "hypothesis": "सोच", "reference_index": 5, "hypothesis_index": 5 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.54542, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Sad", "emotion_confidence": 0.3071862459182739, "duration_seconds": 1.0919999999999987, "mos": 3.0192, "audio_variant": "original", "original_transcript_raw": "मैंने घरों दुखे। ", "original_transcript": "मैंने घरों दुखे।", "retranscribed_transcript": "मुझे घणो दुखे", "backend": "bodhan", "emotion_analyzed_seconds": 1.092, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-187", "energy": { "value": 0.609375, "bucket": "high" }, "audio_url": "audio/utterance-187.wav", "spectrogram_url": "spectrograms/utterance-187.png", "waveform": [ 0.12962, 0.12931, 0.11873, 0.12016, 0.12696, 0.12093, 0.11652, 0.11586, 0.12485, 0.12472, 0.13211, 0.14682, 0.13389, 0.14227, 0.12592, 0.11637, 0.0979, 0.0847, 0.10172, 0.10225, 0.1146, 0.11106, 0.12155, 0.10452, 0.11881, 0.11618, 0.12398, 0.11679, 0.14414, 0.1452, 0.15476, 0.16599, 0.1525, 0.1615, 0.1733, 0.18418, 0.14817, 0.13759, 0.1349, 0.10401, 0.10318, 0.06447, 0.06484, 0.06625, 0.04305, 0.0476, 0.03983, 0.03636, 0.05345, 0.10675, 0.05051, 0.10461, 0.14903, 0.1292, 0.1179, 0.1389, 0.1187, 0.16945, 0.13983, 0.12424, 0.12937, 0.1435, 0.12708, 0.13148, 0.10556, 0.13249, 0.17062, 0.13854, 0.12167, 0.14, 0.13478, 0.10931, 0.10265, 0.12501, 0.13328, 0.11902, 0.13378, 0.13454, 0.13995, 0.12254, 0.10489, 0.12318, 0.11872, 0.13859, 0.11767, 0.11705, 0.13098, 0.13279, 0.15486, 0.14727, 0.12255, 0.13189, 0.1074, 0.08494, 0.06835, 0.07407, 0.05784, 0.05321, 0.05682, 0.05459, 0.05596, 0.04454, 0.05596, 0.09965, 0.10696, 0.11605, 0.11952, 0.143, 0.11489, 0.11985, 0.10891, 0.0948, 0.12373, 0.09016, 0.11423, 0.08569, 0.05936, 0.04248, 0.03828, 0.03111, 0.03357, 0.0188, 0.03545, 0.03541, 0.03514, 0.02572, 0.02926, 0.03921, 0.07198, 0.03844, 0.0403, 0.04277, 0.0482, 0.06116, 0.04518, 0.04735, 0.04152, 0.04081, 0.04244, 0.04563, 0.06466, 0.05503, 0.08382, 0.08239, 0.08723, 0.07974, 0.08236, 0.08332, 0.10166, 0.09785, 0.082, 0.08345, 0.10449, 0.09821, 0.07507, 0.07453, 0.08985, 0.0477, 0.04806, 0.04682, 0.03295, 0.04134, 0.03919, 0.03186, 0.03234, 0.03062, 0.03014, 0.02804, 0.0199, 0.0331, 0.02379, 0.02393, 0.01719, 0.02155, 0.01935, 0.02024, 0.02494, 0.01948, 0.01466, 0.01564 ], "comparison": { "original": "मैंने घरों दुखे।", "retranscribed": "मुझे घणो दुखे", "reference_tokens": [ "मैंने", "घरों", "दुखे" ], "hypothesis_tokens": [ "मुझे", "घणो", "दुखे" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 0, "hits": 1, "reference_words": 3, "hypothesis_words": 3, "edits": 2 }, "wer": 0.6666666666666666, "wer_percent": 66.66666666666666, "alignment": [ { "op": "substitute", "reference": "मैंने", "hypothesis": "मुझे", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "घरों", "hypothesis": "घणो", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "दुखे", "hypothesis": "दुखे", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.18418, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Sad", "emotion_confidence": 0.5502135753631592, "duration_seconds": 3.891, "mos": 3.8198, "audio_variant": "cleaned", "original_transcript_raw": "हर रोज हो जाता हूँ नेट साफ नहीं होता है मेरा पेट", "original_transcript": "हर रोज हो जाता हूँ नेट साफ नहीं होता है मेरा पेट", "retranscribed_transcript": "हर रोज़ हो जाता हूँ लेट साफ़ नहीं होता है मेरा पेट", "backend": "bodhan", "emotion_analyzed_seconds": 3.891, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-188", "energy": { "value": 0.63671875, "bucket": "high" }, "audio_url": "audio/utterance-188.wav", "spectrogram_url": "spectrograms/utterance-188.png", "waveform": [ 0.02364, 0.13345, 0.21166, 0.23442, 0.33147, 0.2753, 0.2521, 0.15986, 0.14201, 0.07948, 0.07301, 0.08104, 0.10669, 0.17126, 0.21597, 0.23091, 0.23675, 0.21276, 0.20294, 0.19336, 0.09238, 0.07105, 0.04884, 0.07525, 0.1169, 0.13829, 0.15414, 0.15348, 0.13933, 0.14228, 0.1118, 0.06429, 0.10892, 0.1996, 0.24956, 0.22892, 0.21398, 0.15171, 0.01796, 0.00193, 0.00013, 0.01073, 0.18855, 0.23714, 0.25042, 0.23198, 0.19993, 0.14562, 0.10604, 0.11036, 0.12046, 0.12421, 0.11362, 0.073, 0.04056, 0.04064, 0.03539, 0.04575, 0.06136, 0.07518, 0.07589, 0.06527, 0.05762, 0.05153, 0.04754, 0.02274, 0.00379, 0.00016, 0.00015, 0.01691, 0.00706, 0.00325, 0.00097, 0.00053, 0.00038, 0.00026, 0.0002, 0.00011, 6e-05, 5e-05, 5e-05, 4e-05, 4e-05, 3e-05, 3e-05, 3e-05, 0.00042, 0.01183, 0.0171, 0.01893, 0.02252, 0.03009, 0.09367, 0.23666, 0.21859, 0.23595, 0.24421, 0.26875, 0.28457, 0.30873, 0.30831, 0.23184, 0.04476, 0.01122, 0.00071, 0.00751, 0.02325, 0.04887, 0.06322, 0.063, 0.06083, 0.0844, 0.08572, 0.07744, 0.05245, 0.0442, 0.03973, 0.04247, 0.03851, 0.06209, 0.08861, 0.1037, 0.08703, 0.01933, 0.00199, 0.00045, 0.0002, 0.0012, 0.03675, 0.04187, 0.04743, 0.05073, 0.04751, 0.04815, 0.03849, 0.02551, 0.00765, 0.00497, 0.00717, 0.01443, 0.04261, 0.04535, 0.05003, 0.04764, 0.02249, 0.02068, 0.04024, 0.04152, 0.05397, 0.04693, 0.04383, 0.02633, 0.00131, 0.00024, 0.00013, 0.0001, 7e-05, 6e-05, 4e-05, 5e-05, 0.00169, 0.06644, 0.10419, 0.11337, 0.10909, 0.10722, 0.12021, 0.14551, 0.13742, 0.03375, 0.01885, 0.00284, 0.00023, 0.0001, 0.00543, 0.00281, 0.0018, 0.0009, 0.00256, 0.03536 ], "comparison": { "original": "हर रोज हो जाता हूँ नेट साफ नहीं होता है मेरा पेट", "retranscribed": "हर रोज़ हो जाता हूँ लेट साफ़ नहीं होता है मेरा पेट", "reference_tokens": [ "हर", "रोज", "हो", "जाता", "हूँ", "नेट", "साफ", "नहीं", "होता", "है", "मेरा", "पेट" ], "hypothesis_tokens": [ "हर", "रोज़", "हो", "जाता", "हूँ", "लेट", "साफ़", "नहीं", "होता", "है", "मेरा", "पेट" ], "counts": { "substitutions": 3, "deletions": 0, "insertions": 0, "hits": 9, "reference_words": 12, "hypothesis_words": 12, "edits": 3 }, "wer": 0.25, "wer_percent": 25.0, "alignment": [ { "op": "equal", "reference": "हर", "hypothesis": "हर", "reference_index": 0, "hypothesis_index": 0 }, { "op": "substitute", "reference": "रोज", "hypothesis": "रोज़", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "हो", "hypothesis": "हो", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "जाता", "hypothesis": "जाता", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "हूँ", "hypothesis": "हूँ", "reference_index": 4, "hypothesis_index": 4 }, { "op": "substitute", "reference": "नेट", "hypothesis": "लेट", "reference_index": 5, "hypothesis_index": 5 }, { "op": "substitute", "reference": "साफ", "hypothesis": "साफ़", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "नहीं", "hypothesis": "नहीं", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "होता", "hypothesis": "होता", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "है", "hypothesis": "है", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "मेरा", "hypothesis": "मेरा", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "पेट", "hypothesis": "पेट", "reference_index": 11, "hypothesis_index": 11 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.33147, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Surprised", "emotion_confidence": 0.31967446208000183, "duration_seconds": 0.7169999999999987, "mos": 3.9351, "audio_variant": "original", "original_transcript_raw": "Что ты", "original_transcript": "Что ты", "retranscribed_transcript": "ज्योति", "backend": "bodhan", "emotion_analyzed_seconds": 0.717, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-189", "energy": { "value": 0.5, "bucket": "low" }, "audio_url": "audio/utterance-189.wav", "spectrogram_url": "spectrograms/utterance-189.png", "waveform": [ 0.00807, 0.01461, 0.02979, 0.0414, 0.06152, 0.05412, 0.05012, 0.05927, 0.07779, 0.08263, 0.12834, 0.0722, 0.09077, 0.10434, 0.06855, 0.10476, 0.06959, 0.06457, 0.0595, 0.07803, 0.07542, 0.10074, 0.0885, 0.11491, 0.09814, 0.09001, 0.08762, 0.08024, 0.09731, 0.06948, 0.07696, 0.04566, 0.03194, 0.03467, 0.03226, 0.02893, 0.02678, 0.02312, 0.02387, 0.02383, 0.02542, 0.03114, 0.0242, 0.02404, 0.01552, 0.01307, 0.00935, 0.00786, 0.00557, 0.00454, 0.00366, 0.00249, 0.00503, 0.00551, 0.00528, 0.00285, 0.00301, 0.00284, 0.00373, 0.00285, 0.00161, 0.00223, 0.00279, 0.00181, 0.00117, 0.00115, 0.00077, 0.00137, 0.0013, 0.00105, 0.00102, 0.00126, 0.00123, 0.00101, 0.00121, 0.002, 0.00242, 0.01178, 0.01116, 0.01224, 0.02254, 0.0205, 0.03473, 0.03199, 0.02816, 0.04247, 0.03492, 0.03059, 0.04226, 0.07356, 0.06662, 0.08151, 0.05788, 0.08175, 0.07959, 0.05747, 0.07465, 0.05807, 0.06668, 0.06508, 0.06045, 0.05786, 0.06052, 0.05255, 0.06033, 0.06846, 0.06802, 0.04247, 0.04494, 0.04181, 0.04559, 0.05222, 0.05048, 0.06386, 0.0486, 0.05903, 0.07853, 0.04332, 0.08767, 0.06472, 0.04679, 0.07962, 0.07681, 0.08294, 0.11044, 0.07703, 0.08068, 0.08089, 0.06975, 0.07343, 0.05858, 0.05599, 0.07006, 0.03505, 0.0456, 0.0414, 0.04914, 0.03997, 0.03025, 0.0421, 0.02942, 0.02262, 0.02705, 0.0331, 0.01851, 0.0229, 0.01672, 0.01385, 0.02426, 0.02486, 0.01561, 0.01746, 0.009, 0.01523, 0.0088, 0.00847, 0.00416, 0.00286, 0.00345, 0.00224, 0.00144, 0.00192, 0.00212, 0.00114, 0.00154, 0.00184, 0.00081, 0.00136, 0.00107, 0.00149, 0.00171, 0.00252, 0.00324, 0.00354, 0.0069, 0.00683, 0.01147, 0.0137, 0.01918, 0.02436 ], "comparison": { "original": "Что ты", "retranscribed": "ज्योति", "reference_tokens": [ "что", "ты" ], "hypothesis_tokens": [ "ज्योति" ], "counts": { "substitutions": 1, "deletions": 1, "insertions": 0, "hits": 0, "reference_words": 2, "hypothesis_words": 1, "edits": 2 }, "wer": 1.0, "wer_percent": 100.0, "alignment": [ { "op": "delete", "reference": "что", "hypothesis": null, "reference_index": 0, "hypothesis_index": null }, { "op": "substitute", "reference": "ты", "hypothesis": "ज्योति", "reference_index": 1, "hypothesis_index": 0 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.12834, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Surprised", "emotion_confidence": 0.2874341309070587, "duration_seconds": 4.4199999999999875, "mos": 3.3788, "audio_variant": "cleaned", "original_transcript_raw": "तब सही सलामत घर आ गए हैं तो हम ऋषि को यात्रा पर ले जा रहे हैं। ", "original_transcript": "तब सही सलामत घर आ गए हैं तो हम ऋषि को यात्रा पर ले जा रहे हैं।", "retranscribed_transcript": "सब सही सलामत घर आ गए हैं तो हम ऋषि को यात्रा पर ले जा रहे हैं ओह", "backend": "bodhan", "emotion_analyzed_seconds": 4.42, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-190", "energy": { "value": 0.56640625, "bucket": "medium" }, "audio_url": "audio/utterance-190.wav", "spectrogram_url": "spectrograms/utterance-190.png", "waveform": [ 0.09814, 0.03593, 0.29878, 0.28037, 0.30885, 0.1149, 0.00634, 0.05913, 0.07353, 0.16963, 0.12721, 0.29134, 0.37026, 0.35701, 0.26155, 0.26438, 0.32254, 0.37474, 0.35062, 0.1145, 0.07534, 0.06072, 0.21569, 0.29233, 0.27778, 0.25177, 0.32809, 0.3223, 0.45741, 0.34382, 0.1914, 0.19656, 0.35913, 0.3879, 0.13632, 0.01287, 0.00297, 0.00165, 0.10423, 0.04548, 0.11471, 0.17862, 0.24316, 0.31611, 0.3064, 0.27086, 0.48452, 0.5474, 0.58987, 0.63203, 0.33213, 0.17185, 0.063, 0.21908, 0.30025, 0.29261, 0.19985, 0.2045, 0.2191, 0.20834, 0.23304, 0.23762, 0.21088, 0.11497, 0.0275, 0.00585, 0.00067, 0.00041, 7e-05, 5e-05, 6e-05, 3e-05, 2e-05, 2e-05, 0.02334, 0.22697, 0.22433, 0.25493, 0.34513, 0.30089, 0.30985, 0.31713, 0.24629, 0.14491, 0.20687, 0.27945, 0.24189, 0.13948, 0.16181, 0.16034, 0.14274, 0.14273, 0.29401, 0.26654, 0.0491, 0.00374, 0.04233, 0.26789, 0.50912, 0.50121, 0.43894, 0.3979, 0.08624, 0.00393, 0.00057, 0.0003, 0.00011, 4e-05, 3e-05, 3e-05, 2e-05, 2e-05, 5e-05, 6e-05, 2e-05, 0.00012, 0.00203, 0.03284, 0.08827, 0.18966, 0.20387, 0.15107, 0.12281, 0.11405, 0.00653, 0.00113, 0.06835, 0.09553, 0.34555, 0.39018, 0.41012, 0.2467, 0.00791, 0.00456, 0.31131, 0.36371, 0.31204, 0.1279, 0.11722, 0.26353, 0.285, 0.2664, 0.17875, 0.06018, 0.14002, 0.17277, 0.17312, 0.18914, 0.16291, 0.11644, 0.12449, 0.08499, 0.15437, 0.18396, 0.15611, 0.12679, 0.09727, 0.03449, 0.00476, 0.00014, 3e-05, 3e-05, 1e-05, 1e-05, 0.28907, 0.15194, 0.13526, 0.21037, 0.23045, 0.19847, 0.16857, 0.23202, 0.26009, 0.26741, 0.26826, 0.24556, 0.30042, 0.29441, 0.31634, 0.46712 ], "comparison": { "original": "तब सही सलामत घर आ गए हैं तो हम ऋषि को यात्रा पर ले जा रहे हैं।", "retranscribed": "सब सही सलामत घर आ गए हैं तो हम ऋषि को यात्रा पर ले जा रहे हैं ओह", "reference_tokens": [ "तब", "सही", "सलामत", "घर", "आ", "गए", "हैं", "तो", "हम", "ऋषि", "को", "यात्रा", "पर", "ले", "जा", "रहे", "हैं" ], "hypothesis_tokens": [ "सब", "सही", "सलामत", "घर", "आ", "गए", "हैं", "तो", "हम", "ऋषि", "को", "यात्रा", "पर", "ले", "जा", "रहे", "हैं", "ओह" ], "counts": { "substitutions": 1, "deletions": 0, "insertions": 1, "hits": 16, "reference_words": 17, "hypothesis_words": 18, "edits": 2 }, "wer": 0.11764705882352941, "wer_percent": 11.76470588235294, "alignment": [ { "op": "substitute", "reference": "तब", "hypothesis": "सब", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "सही", "hypothesis": "सही", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "सलामत", "hypothesis": "सलामत", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "घर", "hypothesis": "घर", "reference_index": 3, "hypothesis_index": 3 }, { "op": "equal", "reference": "आ", "hypothesis": "आ", "reference_index": 4, "hypothesis_index": 4 }, { "op": "equal", "reference": "गए", "hypothesis": "गए", "reference_index": 5, "hypothesis_index": 5 }, { "op": "equal", "reference": "हैं", "hypothesis": "हैं", "reference_index": 6, "hypothesis_index": 6 }, { "op": "equal", "reference": "तो", "hypothesis": "तो", "reference_index": 7, "hypothesis_index": 7 }, { "op": "equal", "reference": "हम", "hypothesis": "हम", "reference_index": 8, "hypothesis_index": 8 }, { "op": "equal", "reference": "ऋषि", "hypothesis": "ऋषि", "reference_index": 9, "hypothesis_index": 9 }, { "op": "equal", "reference": "को", "hypothesis": "को", "reference_index": 10, "hypothesis_index": 10 }, { "op": "equal", "reference": "यात्रा", "hypothesis": "यात्रा", "reference_index": 11, "hypothesis_index": 11 }, { "op": "equal", "reference": "पर", "hypothesis": "पर", "reference_index": 12, "hypothesis_index": 12 }, { "op": "equal", "reference": "ले", "hypothesis": "ले", "reference_index": 13, "hypothesis_index": 13 }, { "op": "equal", "reference": "जा", "hypothesis": "जा", "reference_index": 14, "hypothesis_index": 14 }, { "op": "equal", "reference": "रहे", "hypothesis": "रहे", "reference_index": 15, "hypothesis_index": 15 }, { "op": "equal", "reference": "हैं", "hypothesis": "हैं", "reference_index": 16, "hypothesis_index": 16 }, { "op": "insert", "reference": null, "hypothesis": "ओह", "reference_index": null, "hypothesis_index": 17 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.63203, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Surprised", "emotion_confidence": 0.455104798078537, "duration_seconds": 0.5809999999999995, "mos": 3.3716, "audio_variant": "original", "original_transcript_raw": "मंदिर में", "original_transcript": "मंदिर में", "retranscribed_transcript": "मंदिर में", "backend": "bodhan", "emotion_analyzed_seconds": 0.581, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-191", "energy": { "value": 0.56640625, "bucket": "medium" }, "audio_url": "audio/utterance-191.wav", "spectrogram_url": "spectrograms/utterance-191.png", "waveform": [ 0.30953, 0.29884, 0.26971, 0.31276, 0.30393, 0.1906, 0.28379, 0.28149, 0.29706, 0.2366, 0.25409, 0.17252, 0.16796, 0.19396, 0.20355, 0.19667, 0.1962, 0.19399, 0.17492, 0.19783, 0.20808, 0.17818, 0.20589, 0.21058, 0.15315, 0.22207, 0.21931, 0.14422, 0.22136, 0.22112, 0.13992, 0.23032, 0.2241, 0.15154, 0.22631, 0.22394, 0.21867, 0.2239, 0.22767, 0.22043, 0.20064, 0.22238, 0.22423, 0.14987, 0.21921, 0.2054, 0.15889, 0.19029, 0.17386, 0.15288, 0.15984, 0.13619, 0.11407, 0.11337, 0.14089, 0.12585, 0.16172, 0.20757, 0.25224, 0.27033, 0.29146, 0.26466, 0.27945, 0.26271, 0.27311, 0.26251, 0.24142, 0.23445, 0.22701, 0.23834, 0.24275, 0.24115, 0.2627, 0.24652, 0.22212, 0.25986, 0.23341, 0.21109, 0.17163, 0.15896, 0.14741, 0.13141, 0.13709, 0.15455, 0.15916, 0.14769, 0.15561, 0.15341, 0.14988, 0.15297, 0.15567, 0.17098, 0.18498, 0.1852, 0.19816, 0.17203, 0.19884, 0.1807, 0.16351, 0.15612, 0.14747, 0.13948, 0.12918, 0.13923, 0.14196, 0.14475, 0.15223, 0.15203, 0.15246, 0.1533, 0.13069, 0.13811, 0.13964, 0.13718, 0.13497, 0.13212, 0.13629, 0.14062, 0.14547, 0.15683, 0.18225, 0.18602, 0.168, 0.16993, 0.16516, 0.17106, 0.16369, 0.17369, 0.17909, 0.18956, 0.19098, 0.17591, 0.18527, 0.17906, 0.18596, 0.18687, 0.17039, 0.18848, 0.1951, 0.18604, 0.19957, 0.16898, 0.17585, 0.16201, 0.18505, 0.16794, 0.16366, 0.16198, 0.14782, 0.17332, 0.13215, 0.13455, 0.11152, 0.08078, 0.08954, 0.05216, 0.05612, 0.04509, 0.04763, 0.04064, 0.02874, 0.03345, 0.01732, 0.0202, 0.01905, 0.02083, 0.017, 0.01144, 0.00979, 0.00654, 0.00509, 0.00695, 0.00788, 0.00375, 0.00407, 0.00398, 0.00364, 0.0014, 0.00319, 0.0029 ], "comparison": { "original": "मंदिर में", "retranscribed": "मंदिर में", "reference_tokens": [ "मंदिर", "में" ], "hypothesis_tokens": [ "मंदिर", "में" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 2, "reference_words": 2, "hypothesis_words": 2, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "मंदिर", "hypothesis": "मंदिर", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "में", "hypothesis": "में", "reference_index": 1, "hypothesis_index": 1 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.31276, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Surprised", "emotion_confidence": 0.32939448952674866, "duration_seconds": 0.7680000000000007, "mos": 3.5303, "audio_variant": "original", "original_transcript_raw": "जी पिता जी", "original_transcript": "जी पिता जी", "retranscribed_transcript": "जी पिता जी", "backend": "bodhan", "emotion_analyzed_seconds": 0.768, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-192", "energy": { "value": 0.5625, "bucket": "medium" }, "audio_url": "audio/utterance-192.wav", "spectrogram_url": "spectrograms/utterance-192.png", "waveform": [ 0.05643, 0.05938, 0.05518, 0.0436, 0.0292, 0.01503, 0.02565, 0.06413, 0.11507, 0.17462, 0.15094, 0.15773, 0.23275, 0.30149, 0.3313, 0.20509, 0.21915, 0.17732, 0.19655, 0.19189, 0.13641, 0.12259, 0.08974, 0.06182, 0.06889, 0.0747, 0.13628, 0.14696, 0.14416, 0.14473, 0.18357, 0.1738, 0.15363, 0.16152, 0.13796, 0.1275, 0.11484, 0.10055, 0.05752, 0.04577, 0.02736, 0.02429, 0.01817, 0.00915, 0.00939, 0.00728, 0.00651, 0.00717, 0.00675, 0.00615, 0.00589, 0.00383, 0.00342, 0.00284, 0.00294, 0.00219, 0.00228, 0.03283, 0.04159, 0.02646, 0.06026, 0.07765, 0.12457, 0.12536, 0.10148, 0.0811, 0.07572, 0.06039, 0.04363, 0.01975, 0.00791, 0.00571, 0.00616, 0.01852, 0.01186, 0.00314, 0.00349, 0.00381, 0.00419, 0.08144, 0.07901, 0.02053, 0.11441, 0.15326, 0.17833, 0.19742, 0.20325, 0.18739, 0.18217, 0.16961, 0.17333, 0.17415, 0.17811, 0.17513, 0.14763, 0.14553, 0.13199, 0.14451, 0.16389, 0.1203, 0.12661, 0.14358, 0.13115, 0.13376, 0.12692, 0.08856, 0.07004, 0.07073, 0.06151, 0.05537, 0.05281, 0.04055, 0.02326, 0.017, 0.01663, 0.02036, 0.06589, 0.12804, 0.135, 0.20148, 0.19242, 0.1852, 0.16578, 0.28472, 0.15221, 0.17216, 0.12907, 0.14437, 0.09793, 0.09914, 0.12139, 0.16118, 0.17251, 0.1946, 0.19713, 0.19702, 0.18973, 0.15416, 0.13931, 0.13101, 0.13625, 0.09132, 0.08014, 0.07055, 0.06879, 0.06145, 0.05982, 0.04265, 0.03735, 0.04001, 0.02938, 0.03306, 0.03669, 0.0344, 0.03187, 0.0291, 0.0182, 0.02069, 0.02799, 0.02025, 0.02174, 0.02544, 0.01261, 0.01431, 0.01337, 0.01333, 0.01175, 0.01164, 0.00758, 0.00698, 0.00385, 0.00582, 0.00461, 0.00307, 0.00261, 0.00461, 0.00321, 0.00237, 0.00287, 0.00285 ], "comparison": { "original": "जी पिता जी", "retranscribed": "जी पिता जी", "reference_tokens": [ "जी", "पिता", "जी" ], "hypothesis_tokens": [ "जी", "पिता", "जी" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 3, "reference_words": 3, "hypothesis_words": 3, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "जी", "hypothesis": "जी", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "पिता", "hypothesis": "पिता", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "जी", "hypothesis": "जी", "reference_index": 2, "hypothesis_index": 2 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.3313, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Surprised", "emotion_confidence": 0.31252744793891907, "duration_seconds": 0.9390000000000214, "mos": 3.0157, "audio_variant": "cleaned", "original_transcript_raw": "क्यों नहीं बताया उसने? ", "original_transcript": "क्यों नहीं बताया उसने?", "retranscribed_transcript": "क्यों नहीं बताया उसने", "backend": "bodhan", "emotion_analyzed_seconds": 0.939, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-193", "energy": { "value": 0.73828125, "bucket": "high" }, "audio_url": "audio/utterance-193.wav", "spectrogram_url": "spectrograms/utterance-193.png", "waveform": [ 0.53709, 0.54197, 0.47861, 0.49201, 0.46463, 0.43373, 0.3926, 0.24124, 0.0777, 0.05432, 0.00851, 0.00801, 0.00931, 0.0031, 0.00456, 0.01236, 0.04609, 0.05044, 0.03522, 0.02312, 0.01913, 0.01014, 0.0079, 0.02119, 0.07259, 0.08058, 0.07291, 0.18702, 0.28485, 0.24145, 0.214, 0.19212, 0.18473, 0.17328, 0.16697, 0.17165, 0.14094, 0.1631, 0.16545, 0.15907, 0.14201, 0.12762, 0.12626, 0.18675, 0.23594, 0.29562, 0.32337, 0.30913, 0.33642, 0.34904, 0.36727, 0.35707, 0.36313, 0.34395, 0.35903, 0.25116, 0.10721, 0.06554, 0.05599, 0.06552, 0.06453, 0.07726, 0.11028, 0.18053, 0.45447, 0.50049, 0.52643, 0.55889, 0.58717, 0.50923, 0.45927, 0.37379, 0.41825, 0.40386, 0.42105, 0.36914, 0.13466, 0.08245, 0.03479, 0.01592, 0.00515, 0.0047, 0.00343, 0.00434, 0.00215, 0.00143, 0.00134, 0.01295, 0.07754, 0.2225, 0.21091, 0.24736, 0.30854, 0.77898, 0.70593, 0.60958, 0.63669, 0.62642, 0.64114, 0.63664, 0.61809, 0.56438, 0.58907, 0.57798, 0.54511, 0.58961, 0.58452, 0.57058, 0.62953, 0.63633, 0.64323, 0.68296, 0.73394, 0.7135, 0.70788, 0.6936, 0.65437, 0.63534, 0.6125, 0.62418, 0.5901, 0.53109, 0.43491, 0.37261, 0.31914, 0.29432, 0.28408, 0.23503, 0.22594, 0.1752, 0.13623, 0.12919, 0.06302, 0.04924, 0.04962, 0.04921, 0.02728, 0.03138, 0.02728, 0.02519, 0.02476, 0.02571, 0.03029, 0.0343, 0.05258, 0.04924, 0.03862, 0.03082, 0.01204, 0.00481, 0.00192, 0.00073, 0.00052, 0.00041, 0.00074, 0.00152, 0.00968, 0.04233, 0.19581, 0.37371, 0.36965, 0.39932, 0.40834, 0.5172, 0.53377, 0.55093, 0.53863, 0.50335, 0.49987, 0.49077, 0.49848, 0.44115, 0.47704, 0.38172, 0.31781, 0.38363, 0.34853, 0.28135, 0.42439, 0.50046 ], "comparison": { "original": "क्यों नहीं बताया उसने?", "retranscribed": "क्यों नहीं बताया उसने", "reference_tokens": [ "क्यों", "नहीं", "बताया", "उसने" ], "hypothesis_tokens": [ "क्यों", "नहीं", "बताया", "उसने" ], "counts": { "substitutions": 0, "deletions": 0, "insertions": 0, "hits": 4, "reference_words": 4, "hypothesis_words": 4, "edits": 0 }, "wer": 0.0, "wer_percent": 0.0, "alignment": [ { "op": "equal", "reference": "क्यों", "hypothesis": "क्यों", "reference_index": 0, "hypothesis_index": 0 }, { "op": "equal", "reference": "नहीं", "hypothesis": "नहीं", "reference_index": 1, "hypothesis_index": 1 }, { "op": "equal", "reference": "बताया", "hypothesis": "बताया", "reference_index": 2, "hypothesis_index": 2 }, { "op": "equal", "reference": "उसने", "hypothesis": "उसने", "reference_index": 3, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.77898, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Surprised", "emotion_confidence": 0.3749614655971527, "duration_seconds": 1.5879999999999939, "mos": 2.8567, "audio_variant": "cleaned", "original_transcript_raw": "Jub objeti", "original_transcript": "Jub objeti", "retranscribed_transcript": "ये उठिए उठिए उठिए", "backend": "bodhan", "emotion_analyzed_seconds": 1.588, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-194", "energy": { "value": 0.6484375, "bucket": "high" }, "audio_url": "audio/utterance-194.wav", "spectrogram_url": "spectrograms/utterance-194.png", "waveform": [ 0.00102, 0.00087, 0.00044, 0.00041, 0.00047, 0.00014, 0.00011, 0.00034, 0.00168, 0.03489, 0.08752, 0.08554, 0.09442, 0.07916, 0.06647, 0.06206, 0.06233, 0.08933, 0.08944, 0.13125, 0.27321, 0.34564, 0.48072, 0.56481, 0.5178, 0.56299, 0.50559, 0.43655, 0.30384, 0.29167, 0.29405, 0.21468, 0.18245, 0.05655, 0.0107, 0.00105, 0.00061, 0.00047, 0.0003, 0.00025, 0.00022, 0.00019, 0.00015, 0.00024, 0.00044, 0.00086, 0.00035, 0.00018, 0.00014, 0.00025, 0.00072, 0.03996, 0.56259, 0.62708, 0.6188, 0.64213, 0.64993, 0.46574, 0.38371, 0.32862, 0.17089, 0.11079, 0.04253, 0.00581, 0.00489, 0.04075, 0.08257, 0.1247, 0.11271, 0.19693, 0.42838, 0.56771, 0.52738, 0.39902, 0.45432, 0.53329, 0.61121, 0.5142, 0.49349, 0.51346, 0.54586, 0.51101, 0.52291, 0.60099, 0.22551, 0.15222, 0.12682, 0.08044, 0.02387, 0.0048, 0.00213, 0.08128, 0.08394, 0.08563, 0.05777, 0.09788, 0.14744, 0.24234, 0.38459, 0.40188, 0.4191, 0.41659, 0.46473, 0.4249, 0.30259, 0.16172, 0.10663, 0.07061, 0.05423, 0.05056, 0.04977, 0.04716, 0.03746, 0.03378, 0.01656, 0.01943, 0.01207, 0.00363, 0.00134, 0.00044, 0.00025, 0.00019, 0.00015, 0.00013, 0.00019, 0.00068, 0.00296, 0.42587, 0.58048, 0.52617, 0.59766, 0.55956, 0.52145, 0.41135, 0.06137, 0.01694, 0.0045, 0.04066, 0.07867, 0.0846, 0.0827, 0.04018, 0.04676, 0.04609, 0.04851, 0.03683, 0.39957, 0.5655, 0.46584, 0.38459, 0.3036, 0.3053, 0.20728, 0.09196, 0.02038, 0.00602, 0.00259, 0.00124, 0.00081, 0.00042, 0.00047, 0.00028, 0.00018, 0.00014, 0.00011, 0.00013, 0.00011, 8e-05, 7e-05, 7e-05, 6e-05, 6e-05, 6e-05, 6e-05, 0.00014, 0.00031, 0.00054, 0.00078, 0.00055, 0.00112 ], "comparison": { "original": "Jub objeti", "retranscribed": "ये उठिए उठिए उठिए", "reference_tokens": [ "jub", "objeti" ], "hypothesis_tokens": [ "ये", "उठिए", "उठिए", "उठिए" ], "counts": { "substitutions": 2, "deletions": 0, "insertions": 2, "hits": 0, "reference_words": 2, "hypothesis_words": 4, "edits": 4 }, "wer": 2.0, "wer_percent": 200.0, "alignment": [ { "op": "insert", "reference": null, "hypothesis": "ये", "reference_index": null, "hypothesis_index": 0 }, { "op": "insert", "reference": null, "hypothesis": "उठिए", "reference_index": null, "hypothesis_index": 1 }, { "op": "substitute", "reference": "jub", "hypothesis": "उठिए", "reference_index": 0, "hypothesis_index": 2 }, { "op": "substitute", "reference": "objeti", "hypothesis": "उठिए", "reference_index": 1, "hypothesis_index": 3 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.64993, "audio_sample_format": "pcm16" }, { "language": "Hindi", "emotion": "Surprised", "emotion_confidence": 0.5114493370056152, "duration_seconds": 9.881, "mos": 3.255, "audio_variant": "cleaned", "original_transcript_raw": "थैंक्स सर बास आज जी कॉन्सेप्ट बहुत बढ़िया था और बहुत यूनीक और बकरे टाइप का कि कॉक्रोच और पूल का रोमांस आई मीन अनबिलीवेबल", "original_transcript": "थैंक्स सर बास आज जी कॉन्सेप्ट बहुत बढ़िया था और बहुत यूनीक और बकरे टाइप का कि कॉक्रोच और पूल का रोमांस आई मीन अनबिलीवेबल", "retranscribed_transcript": "थैंक्स अरबाज़ हार जी कॉन्सेप्ट बहुत बढ़िया था और बहुत यूनिक और वखरे टाइप का कि कॉकरोच और पूल का रोमांस आई मीन अनबिलीवेबल", "backend": "bodhan", "emotion_analyzed_seconds": 9.881, "emotion_crop_policy": "center_crop_20s", "duration_supplement": false, "id": "utterance-195", "energy": { "value": 0.6953125, "bucket": "high" }, "audio_url": "audio/utterance-195.wav", "spectrogram_url": "spectrograms/utterance-195.png", "waveform": [ 0.19435, 0.4751, 0.52443, 0.127, 0.01675, 0.2971, 0.31132, 0.04615, 0.67236, 0.73004, 0.62987, 0.21681, 0.00622, 0.00047, 0.00018, 9e-05, 0.22843, 0.74985, 0.72343, 0.16202, 0.13902, 0.44908, 0.39499, 0.22661, 0.02279, 0.00323, 0.00018, 0.76397, 0.76718, 0.5603, 0.22793, 0.45981, 0.68921, 0.10891, 0.10609, 0.37093, 0.64881, 0.65865, 0.63869, 0.24553, 0.30291, 0.67479, 0.48708, 0.59342, 0.663, 0.51515, 0.26141, 0.60249, 0.62923, 0.17051, 0.00619, 0.00065, 0.0002, 0.555, 0.69677, 0.66489, 0.10253, 0.3486, 0.46556, 0.61908, 0.69771, 0.48122, 0.26271, 0.30067, 0.36886, 0.44852, 0.31509, 0.46845, 0.52943, 0.44874, 0.34186, 0.08451, 0.58919, 0.60738, 0.53642, 0.38321, 0.29408, 0.1368, 0.07692, 0.04148, 0.34238, 0.70095, 0.59245, 0.1907, 0.44824, 0.5408, 0.38301, 0.61671, 0.58324, 0.46285, 0.05509, 0.45102, 0.38075, 0.06619, 0.34739, 0.35828, 0.02094, 0.00257, 0.00108, 0.05895, 0.54062, 0.50406, 0.39575, 0.06427, 0.0303, 0.45745, 0.44965, 0.4703, 0.4833, 0.38422, 0.10768, 0.52394, 0.5096, 0.37659, 0.01648, 0.0015, 0.00027, 9e-05, 6e-05, 0.06052, 0.28662, 0.29377, 0.47486, 0.36876, 0.37094, 0.33541, 0.02887, 0.00224, 0.00176, 0.00084, 0.00032, 0.54313, 0.59265, 0.55378, 0.40773, 0.28993, 0.34678, 0.35421, 0.29435, 0.12818, 0.52432, 0.54578, 0.58293, 0.44206, 0.33419, 0.14133, 0.03793, 0.4078, 0.5118, 0.38268, 0.37384, 0.35702, 0.11591, 0.01411, 0.01039, 0.00861, 0.00722, 0.00645, 0.00122, 0.00014, 8e-05, 0.19423, 0.55485, 0.53739, 0.55278, 0.23116, 0.23464, 0.08582, 0.37022, 0.39364, 0.2883, 0.46251, 0.43054, 0.38438, 0.40388, 0.16399, 0.28495, 0.34917, 0.1928, 0.07643 ], "comparison": { "original": "थैंक्स सर बास आज जी कॉन्सेप्ट बहुत बढ़िया था और बहुत यूनीक और बकरे टाइप का कि कॉक्रोच और पूल का रोमांस आई मीन अनबिलीवेबल", "retranscribed": "थैंक्स अरबाज़ हार जी कॉन्सेप्ट बहुत बढ़िया था और बहुत यूनिक और वखरे टाइप का कि कॉकरोच और पूल का रोमांस आई मीन अनबिलीवेबल", "reference_tokens": [ "थैंक्स", "सर", "बास", "आज", "जी", "कॉन्सेप्ट", "बहुत", "बढ़िया", "था", "और", "बहुत", "यूनीक", "और", "बकरे", "टाइप", "का", "कि", "कॉक्रोच", "और", "पूल", "का", "रोमांस", "आई", "मीन", "अनबिलीवेबल" ], "hypothesis_tokens": [ "थैंक्स", "अरबाज़", "हार", "जी", "कॉन्सेप्ट", "बहुत", "बढ़िया", "था", "और", "बहुत", "यूनिक", "और", "वखरे", "टाइप", "का", "कि", "कॉकरोच", "और", "पूल", "का", "रोमांस", "आई", "मीन", "अनबिलीवेबल" ], "counts": { "substitutions": 5, "deletions": 1, "insertions": 0, "hits": 19, "reference_words": 25, "hypothesis_words": 24, "edits": 6 }, "wer": 0.24, "wer_percent": 24.0, "alignment": [ { "op": "equal", "reference": "थैंक्स", "hypothesis": "थैंक्स", "reference_index": 0, "hypothesis_index": 0 }, { "op": "delete", "reference": "सर", "hypothesis": null, "reference_index": 1, "hypothesis_index": null }, { "op": "substitute", "reference": "बास", "hypothesis": "अरबाज़", "reference_index": 2, "hypothesis_index": 1 }, { "op": "substitute", "reference": "आज", "hypothesis": "हार", "reference_index": 3, "hypothesis_index": 2 }, { "op": "equal", "reference": "जी", "hypothesis": "जी", "reference_index": 4, "hypothesis_index": 3 }, { "op": "equal", "reference": "कॉन्सेप्ट", "hypothesis": "कॉन्सेप्ट", "reference_index": 5, "hypothesis_index": 4 }, { "op": "equal", "reference": "बहुत", "hypothesis": "बहुत", "reference_index": 6, "hypothesis_index": 5 }, { "op": "equal", "reference": "बढ़िया", "hypothesis": "बढ़िया", "reference_index": 7, "hypothesis_index": 6 }, { "op": "equal", "reference": "था", "hypothesis": "था", "reference_index": 8, "hypothesis_index": 7 }, { "op": "equal", "reference": "और", "hypothesis": "और", "reference_index": 9, "hypothesis_index": 8 }, { "op": "equal", "reference": "बहुत", "hypothesis": "बहुत", "reference_index": 10, "hypothesis_index": 9 }, { "op": "substitute", "reference": "यूनीक", "hypothesis": "यूनिक", "reference_index": 11, "hypothesis_index": 10 }, { "op": "equal", "reference": "और", "hypothesis": "और", "reference_index": 12, "hypothesis_index": 11 }, { "op": "substitute", "reference": "बकरे", "hypothesis": "वखरे", "reference_index": 13, "hypothesis_index": 12 }, { "op": "equal", "reference": "टाइप", "hypothesis": "टाइप", "reference_index": 14, "hypothesis_index": 13 }, { "op": "equal", "reference": "का", "hypothesis": "का", "reference_index": 15, "hypothesis_index": 14 }, { "op": "equal", "reference": "कि", "hypothesis": "कि", "reference_index": 16, "hypothesis_index": 15 }, { "op": "substitute", "reference": "कॉक्रोच", "hypothesis": "कॉकरोच", "reference_index": 17, "hypothesis_index": 16 }, { "op": "equal", "reference": "और", "hypothesis": "और", "reference_index": 18, "hypothesis_index": 17 }, { "op": "equal", "reference": "पूल", "hypothesis": "पूल", "reference_index": 19, "hypothesis_index": 18 }, { "op": "equal", "reference": "का", "hypothesis": "का", "reference_index": 20, "hypothesis_index": 19 }, { "op": "equal", "reference": "रोमांस", "hypothesis": "रोमांस", "reference_index": 21, "hypothesis_index": 20 }, { "op": "equal", "reference": "आई", "hypothesis": "आई", "reference_index": 22, "hypothesis_index": 21 }, { "op": "equal", "reference": "मीन", "hypothesis": "मीन", "reference_index": 23, "hypothesis_index": 22 }, { "op": "equal", "reference": "अनबिलीवेबल", "hypothesis": "अनबिलीवेबल", "reference_index": 24, "hypothesis_index": 23 } ], "normalization": "unicode-nfc-casefold-punctuation-v1" }, "export_format": "mono 16 kHz pcm16 WAV", "source_peak_abs": 0.76718, "audio_sample_format": "pcm16" } ] }