Files
claudetools/projects/radio-show/audio-processor/training-data/transcripts/2017-s9e26/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

567 lines
10 KiB
JSON

{
"num_speakers": 2,
"speaker_map": {
"HOST": "HOST",
"CALLER": "CALLER"
},
"turns": [
{
"speaker": "HOST",
"start": 0.0,
"end": 20.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 15.0,
"end": 25.0,
"confidence": 0.65
},
{
"speaker": "HOST",
"start": 20.0,
"end": 90.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 85.0,
"end": 95.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 90.0,
"end": 195.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 190.0,
"end": 200.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 195.0,
"end": 565.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 560.0,
"end": 625.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 620.0,
"end": 630.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 625.0,
"end": 665.0,
"confidence": 0.6
},
{
"speaker": "HOST",
"start": 660.0,
"end": 1090.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 1085.0,
"end": 1095.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 1090.0,
"end": 1165.0,
"confidence": 0.92
},
{
"speaker": "CALLER",
"start": 1160.0,
"end": 1170.0,
"confidence": 0.81
},
{
"speaker": "HOST",
"start": 1165.0,
"end": 1345.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 1340.0,
"end": 1350.0,
"confidence": 0.82
},
{
"speaker": "HOST",
"start": 1345.0,
"end": 1525.0,
"confidence": 0.95
},
{
"speaker": "CALLER",
"start": 1520.0,
"end": 1560.0,
"confidence": 0.69
},
{
"speaker": "HOST",
"start": 1555.0,
"end": 1920.0,
"confidence": 0.92
},
{
"speaker": "CALLER",
"start": 1915.0,
"end": 1925.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 1920.0,
"end": 2050.0,
"confidence": 0.93
},
{
"speaker": "CALLER",
"start": 2045.0,
"end": 2055.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 2050.0,
"end": 2075.0,
"confidence": 0.94
},
{
"speaker": "CALLER",
"start": 2070.0,
"end": 2085.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 2080.0,
"end": 2140.0,
"confidence": 0.88
},
{
"speaker": "CALLER",
"start": 2135.0,
"end": 2145.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 2140.0,
"end": 2295.0,
"confidence": 0.89
},
{
"speaker": "CALLER",
"start": 2290.0,
"end": 2300.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 2295.0,
"end": 2405.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 2400.0,
"end": 2460.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 2455.0,
"end": 2660.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 2655.0,
"end": 2665.0,
"confidence": 0.67
},
{
"speaker": "HOST",
"start": 2660.0,
"end": 2715.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 2710.0,
"end": 2725.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 2720.0,
"end": 2755.0,
"confidence": 0.92
},
{
"speaker": "CALLER",
"start": 2750.0,
"end": 2760.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 2755.0,
"end": 2970.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 2965.0,
"end": 3030.0,
"confidence": 0.76
},
{
"speaker": "HOST",
"start": 3025.0,
"end": 3045.0,
"confidence": 0.89
},
{
"speaker": "CALLER",
"start": 3040.0,
"end": 3055.0,
"confidence": 0.79
},
{
"speaker": "HOST",
"start": 3050.0,
"end": 3105.0,
"confidence": 0.95
},
{
"speaker": "CALLER",
"start": 3100.0,
"end": 3165.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 3160.0,
"end": 3205.0,
"confidence": 0.95
},
{
"speaker": "CALLER",
"start": 3200.0,
"end": 3210.0,
"confidence": 0.79
},
{
"speaker": "HOST",
"start": 3205.0,
"end": 3385.0,
"confidence": 0.95
},
{
"speaker": "CALLER",
"start": 3380.0,
"end": 3420.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 3415.0,
"end": 3430.0,
"confidence": 0.94
},
{
"speaker": "CALLER",
"start": 3425.0,
"end": 3445.0,
"confidence": 0.8
},
{
"speaker": "HOST",
"start": 3440.0,
"end": 3475.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 3470.0,
"end": 3490.0,
"confidence": 0.8
},
{
"speaker": "HOST",
"start": 3485.0,
"end": 3510.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 3505.0,
"end": 3555.0,
"confidence": 0.67
},
{
"speaker": "HOST",
"start": 3550.0,
"end": 3570.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 3565.0,
"end": 3590.0,
"confidence": 0.48
},
{
"speaker": "HOST",
"start": 3585.0,
"end": 4015.0,
"confidence": 0.95
},
{
"speaker": "CALLER",
"start": 4010.0,
"end": 4020.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 4015.0,
"end": 4075.0,
"confidence": 0.91
},
{
"speaker": "CALLER",
"start": 4070.0,
"end": 4130.0,
"confidence": 0.8
},
{
"speaker": "HOST",
"start": 4125.0,
"end": 4180.0,
"confidence": 0.93
},
{
"speaker": "CALLER",
"start": 4175.0,
"end": 4200.0,
"confidence": 0.78
},
{
"speaker": "HOST",
"start": 4195.0,
"end": 4215.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 4210.0,
"end": 4235.0,
"confidence": 0.81
},
{
"speaker": "HOST",
"start": 4230.0,
"end": 4240.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 4235.0,
"end": 4250.0,
"confidence": 0.81
},
{
"speaker": "HOST",
"start": 4245.0,
"end": 4270.0,
"confidence": 0.92
},
{
"speaker": "CALLER",
"start": 4265.0,
"end": 4280.0,
"confidence": 0.76
},
{
"speaker": "HOST",
"start": 4275.0,
"end": 4295.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 4290.0,
"end": 4305.0,
"confidence": 0.78
},
{
"speaker": "HOST",
"start": 4300.0,
"end": 4360.0,
"confidence": 0.94
},
{
"speaker": "CALLER",
"start": 4355.0,
"end": 4370.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 4365.0,
"end": 4375.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 4370.0,
"end": 4385.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 4380.0,
"end": 4395.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 4390.0,
"end": 4400.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 4395.0,
"end": 4405.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 4400.0,
"end": 4410.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 4405.0,
"end": 4430.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 4425.0,
"end": 4460.0,
"confidence": 0.8
},
{
"speaker": "HOST",
"start": 4455.0,
"end": 4500.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 4495.0,
"end": 4510.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 4505.0,
"end": 4520.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 4515.0,
"end": 4535.0,
"confidence": 0.82
},
{
"speaker": "HOST",
"start": 4530.0,
"end": 4540.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 4535.0,
"end": 4550.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 4545.0,
"end": 4570.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 4565.0,
"end": 4575.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 4570.0,
"end": 4595.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 4590.0,
"end": 4605.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 4600.0,
"end": 4610.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 4605.0,
"end": 4640.0,
"confidence": 0.64
},
{
"speaker": "HOST",
"start": 4635.0,
"end": 5045.0,
"confidence": 0.94
},
{
"speaker": "CALLER",
"start": 5040.0,
"end": 5050.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 5045.0,
"end": 5365.0,
"confidence": 0.86
}
]
}