- Fine-grained speaker analysis (3s windows, 1s hop) across 42min episode - Host voice: 0.90-0.98 similarity (clear positive match) - Callers: 0.65-0.68 (correctly below threshold) - Produced audio/clips: 0.53-0.65 (correctly identified as non-host) - Co-host/other speakers: 0.56-0.62 (correctly identified) - Tuned host_match_threshold from 0.75 to 0.83 based on empirical data - Cross-referenced dips with transcript: correctly identifies callers, show intros, played audio clips, and station breaks - Batch transcription of 7 additional training episodes in progress Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
45 lines
888 B
JSON
45 lines
888 B
JSON
{
|
|
"total_show_time": 2249.61,
|
|
"total_commercial_time": 296.19000000000005,
|
|
"segments": [
|
|
{
|
|
"start": 0.0,
|
|
"end": 2078.81,
|
|
"type": "show_content",
|
|
"confidence": 0.8,
|
|
"label": "",
|
|
"signals": {
|
|
"fingerprint": 0.5,
|
|
"speaker": 0.5,
|
|
"audio_chars": 0.5,
|
|
"structural": 0.8
|
|
}
|
|
},
|
|
{
|
|
"start": 2078.81,
|
|
"end": 2375.0,
|
|
"type": "commercial",
|
|
"confidence": 0.8,
|
|
"label": "",
|
|
"signals": {
|
|
"fingerprint": 0.5,
|
|
"speaker": 0.5,
|
|
"audio_chars": 0.5,
|
|
"structural": 0.5
|
|
}
|
|
},
|
|
{
|
|
"start": 2375.0,
|
|
"end": 2545.8,
|
|
"type": "show_content",
|
|
"confidence": 0.8,
|
|
"label": "",
|
|
"signals": {
|
|
"fingerprint": 0.5,
|
|
"speaker": 0.5,
|
|
"audio_chars": 0.5,
|
|
"structural": 0.8
|
|
}
|
|
}
|
|
]
|
|
} |