Audio processor: validated voice profiling accuracy, tuned threshold

Browse Source

- 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>

...

This commit is contained in:

Mike Swanson

2026-03-21 12:48:25 -07:00

parent 826141a319

commit 6cc9043b8e

228 changed files with 137641 additions and 1 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

55129

projects/radio-show/audio-processor/training-data/transcripts/2010-10-02-hr1/transcript.json Normal file

File diff suppressed because it is too large Load Diff

2135

projects/radio-show/audio-processor/training-data/transcripts/2010-10-02-hr1/transcript.srt Normal file

File diff suppressed because it is too large Load Diff

1

projects/radio-show/audio-processor/training-data/transcripts/2010-10-02-hr1/transcript.txt Normal file

File diff suppressed because one or more lines are too long