mirror of
https://github.com/QuentinFuxa/WhisperLiveKit.git
synced 2026-03-07 14:23:18 +00:00
83d0fa3fac
- 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.
177 lines
2.2 KiB
JSON
177 lines
2.2 KiB
JSON
[
|
|
{
|
|
"word": "Ok,",
|
|
"start": 2.02,
|
|
"end": 2.38
|
|
},
|
|
{
|
|
"word": "là",
|
|
"start": 2.52,
|
|
"end": 2.58
|
|
},
|
|
{
|
|
"word": "c",
|
|
"start": 2.58,
|
|
"end": 2.74
|
|
},
|
|
{
|
|
"word": "'est",
|
|
"start": 2.74,
|
|
"end": 2.76
|
|
},
|
|
{
|
|
"word": "un",
|
|
"start": 2.76,
|
|
"end": 2.86
|
|
},
|
|
{
|
|
"word": "test,",
|
|
"start": 2.86,
|
|
"end": 3.2
|
|
},
|
|
{
|
|
"word": "on",
|
|
"start": 3.34,
|
|
"end": 3.34
|
|
},
|
|
{
|
|
"word": "veut",
|
|
"start": 3.34,
|
|
"end": 3.48
|
|
},
|
|
{
|
|
"word": "voir",
|
|
"start": 3.48,
|
|
"end": 3.86
|
|
},
|
|
{
|
|
"word": "si",
|
|
"start": 3.86,
|
|
"end": 4.14
|
|
},
|
|
{
|
|
"word": "ça",
|
|
"start": 4.14,
|
|
"end": 4.26
|
|
},
|
|
{
|
|
"word": "arrive",
|
|
"start": 4.26,
|
|
"end": 4.36
|
|
},
|
|
{
|
|
"word": "à",
|
|
"start": 4.36,
|
|
"end": 4.5
|
|
},
|
|
{
|
|
"word": "capté",
|
|
"start": 4.5,
|
|
"end": 4.78
|
|
},
|
|
{
|
|
"word": "le",
|
|
"start": 4.78,
|
|
"end": 4.9
|
|
},
|
|
{
|
|
"word": "silence.",
|
|
"start": 4.9,
|
|
"end": 5.44
|
|
},
|
|
{
|
|
"word": "Là",
|
|
"start": 9.24,
|
|
"end": 9.6
|
|
},
|
|
{
|
|
"word": "il",
|
|
"start": 9.6,
|
|
"end": 9.78
|
|
},
|
|
{
|
|
"word": "est",
|
|
"start": 9.78,
|
|
"end": 9.84
|
|
},
|
|
{
|
|
"word": "une",
|
|
"start": 9.84,
|
|
"end": 9.96
|
|
},
|
|
{
|
|
"word": "telle",
|
|
"start": 9.96,
|
|
"end": 10.12
|
|
},
|
|
{
|
|
"word": "seconde",
|
|
"start": 10.12,
|
|
"end": 10.38
|
|
},
|
|
{
|
|
"word": "de",
|
|
"start": 10.38,
|
|
"end": 10.48
|
|
},
|
|
{
|
|
"word": "silence",
|
|
"start": 10.48,
|
|
"end": 10.78
|
|
},
|
|
{
|
|
"word": "et",
|
|
"start": 10.78,
|
|
"end": 11.06
|
|
},
|
|
{
|
|
"word": "je",
|
|
"start": 11.06,
|
|
"end": 11.16
|
|
},
|
|
{
|
|
"word": "vous",
|
|
"start": 11.16,
|
|
"end": 11.32
|
|
},
|
|
{
|
|
"word": "parle.",
|
|
"start": 11.32,
|
|
"end": 11.68
|
|
},
|
|
{
|
|
"word": "Et",
|
|
"start": 13.28,
|
|
"end": 13.64
|
|
},
|
|
{
|
|
"word": "voilà,",
|
|
"start": 13.64,
|
|
"end": 13.96
|
|
},
|
|
{
|
|
"word": "allez",
|
|
"start": 14.36,
|
|
"end": 14.62
|
|
},
|
|
{
|
|
"word": "on",
|
|
"start": 14.62,
|
|
"end": 14.78
|
|
},
|
|
{
|
|
"word": "va",
|
|
"start": 14.78,
|
|
"end": 14.88
|
|
},
|
|
{
|
|
"word": "tester",
|
|
"start": 14.88,
|
|
"end": 15.06
|
|
},
|
|
{
|
|
"word": "ça.",
|
|
"start": 15.06,
|
|
"end": 15.36
|
|
}
|
|
] |