Files
WhisperLiveKit/audio_tests/00_00_30_english_3_speakers.transcript.json
Quentin Fuxa 83d0fa3fac feat: benchmark suite with WER, timestamp accuracy, cross-backend comparison
- Extend test_backend_offline.py with WER and timestamp accuracy metrics
  computed via whisperlivekit.metrics against ground truth transcripts.
- Add --benchmark flag to auto-detect all installed backends and run
  each (backend, policy) combination in sequence.
- Add --policy flag to override the streaming policy.
- Add detect_available_backends() probing faster-whisper, mlx-whisper,
  voxtral-mlx, voxtral (HF), and openai-whisper.
- Add print_cross_backend_comparison() with per-combo averages.
- Add run_benchmark.py for comprehensive multi-model benchmarking.
- Add BENCHMARK.md with full results on Apple M4: speed, WER,
  timestamp accuracy, VAC impact, and recommendations.
- Add ground truth transcript JSON files for all audio test files.
2026-02-22 23:27:50 +01:00

382 lines
4.9 KiB
JSON

[
{
"word": "Transcription",
"start": 0.0,
"end": 0.6
},
{
"word": "technology",
"start": 0.6,
"end": 1.24
},
{
"word": "has",
"start": 1.24,
"end": 1.5
},
{
"word": "improved",
"start": 1.5,
"end": 1.96
},
{
"word": "so",
"start": 1.96,
"end": 2.32
},
{
"word": "much",
"start": 2.32,
"end": 2.68
},
{
"word": "in",
"start": 2.68,
"end": 2.94
},
{
"word": "the",
"start": 2.94,
"end": 3.02
},
{
"word": "past",
"start": 3.02,
"end": 3.24
},
{
"word": "few",
"start": 3.24,
"end": 3.5
},
{
"word": "years.",
"start": 3.5,
"end": 3.96
},
{
"word": "Have",
"start": 4.56,
"end": 4.74
},
{
"word": "you",
"start": 4.74,
"end": 4.9
},
{
"word": "noticed",
"start": 4.9,
"end": 5.26
},
{
"word": "how",
"start": 5.26,
"end": 5.52
},
{
"word": "accurate",
"start": 5.52,
"end": 6.08
},
{
"word": "real",
"start": 6.08,
"end": 6.42
},
{
"word": "-time",
"start": 6.42,
"end": 6.74
},
{
"word": "speech",
"start": 6.74,
"end": 7.24
},
{
"word": "to",
"start": 7.24,
"end": 7.46
},
{
"word": "text",
"start": 7.46,
"end": 7.78
},
{
"word": "is",
"start": 7.78,
"end": 8.0
},
{
"word": "now?",
"start": 8.0,
"end": 8.3
},
{
"word": "Absolutely.",
"start": 8.7,
"end": 9.16
},
{
"word": "I",
"start": 10.04,
"end": 10.38
},
{
"word": "use",
"start": 10.38,
"end": 10.56
},
{
"word": "it",
"start": 10.56,
"end": 10.76
},
{
"word": "all",
"start": 10.76,
"end": 10.9
},
{
"word": "the",
"start": 10.9,
"end": 11.04
},
{
"word": "time",
"start": 11.04,
"end": 11.32
},
{
"word": "for",
"start": 11.32,
"end": 11.54
},
{
"word": "taking",
"start": 11.54,
"end": 11.86
},
{
"word": "notes",
"start": 11.86,
"end": 12.16
},
{
"word": "during",
"start": 12.16,
"end": 12.54
},
{
"word": "meetings.",
"start": 12.54,
"end": 12.94
},
{
"word": "It's",
"start": 13.6,
"end": 13.8
},
{
"word": "amazing",
"start": 13.8,
"end": 14.1
},
{
"word": "how",
"start": 14.1,
"end": 14.48
},
{
"word": "it",
"start": 14.48,
"end": 14.62
},
{
"word": "can",
"start": 14.62,
"end": 14.74
},
{
"word": "recognise",
"start": 14.74,
"end": 15.24
},
{
"word": "different",
"start": 15.24,
"end": 15.68
},
{
"word": "speakers",
"start": 15.68,
"end": 16.16
},
{
"word": "and",
"start": 16.16,
"end": 16.8
},
{
"word": "even",
"start": 16.8,
"end": 17.1
},
{
"word": "add",
"start": 17.1,
"end": 17.44
},
{
"word": "punctuation.",
"start": 17.44,
"end": 18.36
},
{
"word": "Yeah,",
"start": 18.88,
"end": 19.16
},
{
"word": "but",
"start": 19.36,
"end": 19.52
},
{
"word": "sometimes",
"start": 19.52,
"end": 20.16
},
{
"word": "noise",
"start": 20.16,
"end": 20.54
},
{
"word": "can",
"start": 20.54,
"end": 20.8
},
{
"word": "still",
"start": 20.8,
"end": 21.1
},
{
"word": "cause",
"start": 21.1,
"end": 21.44
},
{
"word": "mistakes.",
"start": 21.44,
"end": 21.94
},
{
"word": "Does",
"start": 22.68,
"end": 22.9
},
{
"word": "this",
"start": 22.9,
"end": 23.12
},
{
"word": "system",
"start": 23.12,
"end": 23.46
},
{
"word": "handle",
"start": 23.46,
"end": 23.88
},
{
"word": "that",
"start": 23.88,
"end": 24.12
},
{
"word": "well?",
"start": 24.12,
"end": 24.42
},
{
"word": "It",
"start": 24.42,
"end": 25.32
},
{
"word": "does",
"start": 25.32,
"end": 25.48
},
{
"word": "a",
"start": 25.48,
"end": 25.62
},
{
"word": "pretty",
"start": 25.62,
"end": 25.88
},
{
"word": "good",
"start": 25.88,
"end": 26.08
},
{
"word": "job",
"start": 26.08,
"end": 26.32
},
{
"word": "filtering",
"start": 26.32,
"end": 26.8
},
{
"word": "noise,",
"start": 26.8,
"end": 27.18
},
{
"word": "especially",
"start": 27.36,
"end": 28.0
},
{
"word": "with",
"start": 28.0,
"end": 28.28
},
{
"word": "models",
"start": 28.28,
"end": 28.62
},
{
"word": "that",
"start": 28.62,
"end": 28.94
},
{
"word": "use",
"start": 28.94,
"end": 29.22
},
{
"word": "voice",
"start": 29.22,
"end": 29.54
},
{
"word": "active.",
"start": 29.54,
"end": 29.9
}
]