Files
claudetools/projects/radio-show/audio-processor/training-data/transcripts/2010-10-02-hr1/diarization.json
Mike Swanson 79abef9dc9 radio: diarization pipeline fixes, benchmark setup, test episode set
- Fix voice_profiler threshold bug (HOST label overwrote Unknown unconditionally)
- Audio preload optimization: single ffmpeg per episode, 149.5x realtime on 5070 Ti
- WavLM threshold raised to 0.85 (Mike 0.90-0.99, callers 0.46-0.83)
- Promo/bumper filter: weighted signature scoring, 42->27 clean Q&A pairs
- Text-only Q&A fallback for episodes with no CALLER diarization labels
- TRANSFORMERS_OFFLINE=1 to skip HuggingFace freshness checks
- Add diarize_2018.py for targeted re-run + FTS5 rebuild
- Add benchmark.py + BENCH_SETUP.md for GURU-BEAST-ROG (RTX 4090) comparison
- Commit 9-episode training diarization.json outputs
- Session log: 2026-04-27-diarization-pipeline.md

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-27 13:20:40 -07:00

327 lines
6.0 KiB
JSON

{
"num_speakers": 2,
"speaker_map": {
"HOST": "HOST",
"CALLER": "CALLER"
},
"turns": [
{
"speaker": "HOST",
"start": 0.0,
"end": 30.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 25.0,
"end": 35.0,
"confidence": 0.79
},
{
"speaker": "HOST",
"start": 30.0,
"end": 105.0,
"confidence": 0.95
},
{
"speaker": "CALLER",
"start": 100.0,
"end": 115.0,
"confidence": 0.56
},
{
"speaker": "HOST",
"start": 110.0,
"end": 160.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 155.0,
"end": 170.0,
"confidence": 0.64
},
{
"speaker": "HOST",
"start": 165.0,
"end": 210.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 205.0,
"end": 225.0,
"confidence": 0.79
},
{
"speaker": "HOST",
"start": 220.0,
"end": 235.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 230.0,
"end": 240.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 235.0,
"end": 290.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 285.0,
"end": 320.0,
"confidence": 0.55
},
{
"speaker": "HOST",
"start": 315.0,
"end": 415.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 410.0,
"end": 420.0,
"confidence": 0.8
},
{
"speaker": "HOST",
"start": 415.0,
"end": 440.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 435.0,
"end": 455.0,
"confidence": 0.57
},
{
"speaker": "HOST",
"start": 450.0,
"end": 530.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 525.0,
"end": 535.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 530.0,
"end": 595.0,
"confidence": 0.88
},
{
"speaker": "CALLER",
"start": 590.0,
"end": 605.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 600.0,
"end": 870.0,
"confidence": 0.89
},
{
"speaker": "CALLER",
"start": 865.0,
"end": 930.0,
"confidence": 0.6
},
{
"speaker": "HOST",
"start": 925.0,
"end": 945.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 940.0,
"end": 970.0,
"confidence": 0.54
},
{
"speaker": "HOST",
"start": 965.0,
"end": 1015.0,
"confidence": 0.95
},
{
"speaker": "CALLER",
"start": 1010.0,
"end": 1040.0,
"confidence": 0.49
},
{
"speaker": "HOST",
"start": 1035.0,
"end": 1060.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 1055.0,
"end": 1070.0,
"confidence": 0.65
},
{
"speaker": "HOST",
"start": 1065.0,
"end": 1105.0,
"confidence": 0.88
},
{
"speaker": "CALLER",
"start": 1100.0,
"end": 1120.0,
"confidence": 0.82
},
{
"speaker": "HOST",
"start": 1115.0,
"end": 1225.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 1220.0,
"end": 1230.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 1225.0,
"end": 1265.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 1260.0,
"end": 1275.0,
"confidence": 0.62
},
{
"speaker": "HOST",
"start": 1270.0,
"end": 1310.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 1305.0,
"end": 1320.0,
"confidence": 0.57
},
{
"speaker": "HOST",
"start": 1315.0,
"end": 1340.0,
"confidence": 0.94
},
{
"speaker": "CALLER",
"start": 1335.0,
"end": 1350.0,
"confidence": 0.57
},
{
"speaker": "HOST",
"start": 1345.0,
"end": 1705.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 1700.0,
"end": 1725.0,
"confidence": 0.65
},
{
"speaker": "HOST",
"start": 1720.0,
"end": 1825.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 1820.0,
"end": 1840.0,
"confidence": 0.65
},
{
"speaker": "HOST",
"start": 1835.0,
"end": 1900.0,
"confidence": 0.92
},
{
"speaker": "CALLER",
"start": 1895.0,
"end": 1925.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 1920.0,
"end": 1935.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 1930.0,
"end": 1940.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 1935.0,
"end": 1955.0,
"confidence": 0.88
},
{
"speaker": "CALLER",
"start": 1950.0,
"end": 1960.0,
"confidence": 0.81
},
{
"speaker": "HOST",
"start": 1955.0,
"end": 2050.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 2045.0,
"end": 2055.0,
"confidence": 0.49
},
{
"speaker": "HOST",
"start": 2050.0,
"end": 2455.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 2450.0,
"end": 2465.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 2460.0,
"end": 2675.0,
"confidence": 0.87
}
]
}