Files
claudetools/projects/radio-show/audio-processor/training-data/transcripts/2018-s10e21/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

669 lines
12 KiB
JSON

{
"num_speakers": 2,
"speaker_map": {
"CALLER": "CALLER",
"HOST": "HOST"
},
"turns": [
{
"speaker": "CALLER",
"start": 0.0,
"end": 10.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 5.0,
"end": 20.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 15.0,
"end": 25.0,
"confidence": 0.63
},
{
"speaker": "HOST",
"start": 20.0,
"end": 165.0,
"confidence": 0.99
},
{
"speaker": "CALLER",
"start": 160.0,
"end": 170.0,
"confidence": 0.82
},
{
"speaker": "HOST",
"start": 165.0,
"end": 240.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 235.0,
"end": 250.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 245.0,
"end": 275.0,
"confidence": 0.92
},
{
"speaker": "CALLER",
"start": 270.0,
"end": 290.0,
"confidence": 0.65
},
{
"speaker": "HOST",
"start": 285.0,
"end": 295.0,
"confidence": 0.94
},
{
"speaker": "CALLER",
"start": 290.0,
"end": 305.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 300.0,
"end": 320.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 315.0,
"end": 345.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 340.0,
"end": 350.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 345.0,
"end": 365.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 360.0,
"end": 545.0,
"confidence": 0.95
},
{
"speaker": "CALLER",
"start": 540.0,
"end": 555.0,
"confidence": 0.82
},
{
"speaker": "HOST",
"start": 550.0,
"end": 570.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 565.0,
"end": 585.0,
"confidence": 0.82
},
{
"speaker": "HOST",
"start": 580.0,
"end": 590.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 585.0,
"end": 595.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 590.0,
"end": 625.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 620.0,
"end": 630.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 625.0,
"end": 635.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 630.0,
"end": 650.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 645.0,
"end": 700.0,
"confidence": 0.94
},
{
"speaker": "CALLER",
"start": 695.0,
"end": 745.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 740.0,
"end": 780.0,
"confidence": 0.89
},
{
"speaker": "CALLER",
"start": 775.0,
"end": 785.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 780.0,
"end": 790.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 785.0,
"end": 825.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 820.0,
"end": 830.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 825.0,
"end": 860.0,
"confidence": 0.79
},
{
"speaker": "HOST",
"start": 855.0,
"end": 870.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 865.0,
"end": 895.0,
"confidence": 0.82
},
{
"speaker": "HOST",
"start": 890.0,
"end": 1060.0,
"confidence": 0.91
},
{
"speaker": "CALLER",
"start": 1055.0,
"end": 1065.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 1060.0,
"end": 1115.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 1110.0,
"end": 1120.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 1115.0,
"end": 1240.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 1235.0,
"end": 1250.0,
"confidence": 0.79
},
{
"speaker": "HOST",
"start": 1245.0,
"end": 1255.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 1250.0,
"end": 1260.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 1255.0,
"end": 1270.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 1265.0,
"end": 1275.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 1270.0,
"end": 1340.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 1335.0,
"end": 1345.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 1340.0,
"end": 1350.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 1345.0,
"end": 1355.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 1350.0,
"end": 1435.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 1430.0,
"end": 1450.0,
"confidence": 0.61
},
{
"speaker": "HOST",
"start": 1445.0,
"end": 1595.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 1590.0,
"end": 1605.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 1600.0,
"end": 1610.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 1605.0,
"end": 1620.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 1615.0,
"end": 1635.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 1630.0,
"end": 1640.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 1635.0,
"end": 1650.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 1645.0,
"end": 1675.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 1670.0,
"end": 1875.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 1870.0,
"end": 1890.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 1885.0,
"end": 2020.0,
"confidence": 0.93
},
{
"speaker": "CALLER",
"start": 2015.0,
"end": 2030.0,
"confidence": 0.8
},
{
"speaker": "HOST",
"start": 2025.0,
"end": 2035.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 2030.0,
"end": 2040.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 2035.0,
"end": 2110.0,
"confidence": 0.88
},
{
"speaker": "CALLER",
"start": 2105.0,
"end": 2115.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 2110.0,
"end": 2135.0,
"confidence": 0.89
},
{
"speaker": "CALLER",
"start": 2130.0,
"end": 2195.0,
"confidence": 0.71
},
{
"speaker": "HOST",
"start": 2190.0,
"end": 2375.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 2370.0,
"end": 2385.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 2380.0,
"end": 2670.0,
"confidence": 0.91
},
{
"speaker": "CALLER",
"start": 2665.0,
"end": 2675.0,
"confidence": 0.81
},
{
"speaker": "HOST",
"start": 2670.0,
"end": 2690.0,
"confidence": 0.88
},
{
"speaker": "CALLER",
"start": 2685.0,
"end": 2695.0,
"confidence": 0.7
},
{
"speaker": "HOST",
"start": 2690.0,
"end": 2855.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 2850.0,
"end": 2965.0,
"confidence": 0.75
},
{
"speaker": "HOST",
"start": 2960.0,
"end": 3025.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 3020.0,
"end": 3040.0,
"confidence": 0.77
},
{
"speaker": "HOST",
"start": 3035.0,
"end": 3045.0,
"confidence": 0.85
},
{
"speaker": "CALLER",
"start": 3040.0,
"end": 3050.0,
"confidence": 0.77
},
{
"speaker": "HOST",
"start": 3045.0,
"end": 3060.0,
"confidence": 0.91
},
{
"speaker": "CALLER",
"start": 3055.0,
"end": 3100.0,
"confidence": 0.78
},
{
"speaker": "HOST",
"start": 3095.0,
"end": 3180.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 3175.0,
"end": 3195.0,
"confidence": 0.77
},
{
"speaker": "HOST",
"start": 3190.0,
"end": 3215.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 3210.0,
"end": 3230.0,
"confidence": 0.8
},
{
"speaker": "HOST",
"start": 3225.0,
"end": 3240.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 3235.0,
"end": 3250.0,
"confidence": 0.8
},
{
"speaker": "HOST",
"start": 3245.0,
"end": 3270.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 3265.0,
"end": 3305.0,
"confidence": 0.78
},
{
"speaker": "HOST",
"start": 3300.0,
"end": 3675.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 3670.0,
"end": 3680.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 3675.0,
"end": 3875.0,
"confidence": 0.88
},
{
"speaker": "CALLER",
"start": 3870.0,
"end": 3905.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 3900.0,
"end": 3990.0,
"confidence": 0.95
},
{
"speaker": "CALLER",
"start": 3985.0,
"end": 4000.0,
"confidence": 0.73
},
{
"speaker": "HOST",
"start": 3995.0,
"end": 4145.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 4140.0,
"end": 4165.0,
"confidence": 0.7
},
{
"speaker": "HOST",
"start": 4160.0,
"end": 4180.0,
"confidence": 0.96
},
{
"speaker": "CALLER",
"start": 4175.0,
"end": 4205.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 4200.0,
"end": 4500.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 4495.0,
"end": 4505.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 4500.0,
"end": 4600.0,
"confidence": 0.88
},
{
"speaker": "CALLER",
"start": 4595.0,
"end": 4605.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 4600.0,
"end": 5040.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 5035.0,
"end": 5045.0,
"confidence": 0.81
},
{
"speaker": "HOST",
"start": 5040.0,
"end": 5055.0,
"confidence": 0.93
},
{
"speaker": "CALLER",
"start": 5050.0,
"end": 5105.0,
"confidence": 0.7
},
{
"speaker": "HOST",
"start": 5100.0,
"end": 5300.0,
"confidence": 0.98
}
]
}