Files
claudetools/projects/radio-show/audio-processor/test-data/transcripts/2012-03-10-hr1/diarization.json
Mike Swanson fb683d6a05 radio: rename Tom -> Tara, expand speaker roster
Mike confirmed there is no co-host named "Tom" — the voice in 2014-s6e19
and 2016-s8e43 is Tara. The 5070 Ti session fabricated the Tom identity.
The voice profile itself (44 embeddings, 0.698 cosine vs Mike) is correct;
only the human label was wrong.

Rename swept:
- voice-profiles/tom/ -> voice-profiles/tara/ (git mv preserves all .npy)
- voice-profiles/profiles.json: "Tom" key -> "Tara"
- build_cohost_profile.py: TOM_WINDOWS -> TARA_WINDOWS, COHOST_NAME, comments
- 2026-04-27-qa-extraction-cohost-indexing.md: correction header + body sweep
- 2026-04-27-4090-benchmark-and-test-set.md: closure note
- .claude/memory/radio_show_no_cohost_named_tom.md: resolution + speaker roster

Diarization re-run after rename so speaker_map emits "Cohost: Tara".
Q&A counts unchanged (rename is label-only): 9 pairs across 6 test episodes.

Tara distribution from the post-rename diarization (per-episode % of audio):
  2011-03-12-hr1   140s   5.6%   likely false positive (call-in only)
  2012-03-10-hr1    30s   1.1%   likely false positive (call-in only)
  2012-06-09-hr1   340s  12.8%   suspicious — pending Mike confirm
  2014-s6e19       680s  23.3%   confirmed
  2016-s8e43      1890s  35.5%   confirmed
  2017-s9e30       610s  11.4%   plausible — pending Mike confirm

Broader speaker-roster context Mike provided this session (saved to
memory): the show has had multiple co-hosts (Tara, Randall, Rob) plus
producers/board ops (Andrew, Shannon, Ken, others) who would sometimes
go on-air. Only Tara has a profile so far. Every other speaker is
currently labeled CALLER, which means small CO-HOST attributions in
unexpected episodes (e.g. 2011/2012) may actually be a producer rather
than a false positive — Mike to spot-check.

Action item before full-archive run: build profiles for Randall, Rob,
and the named producers to avoid systematic Q&A false positives in
early-years and 2018/2019 episodes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-27 15:11:03 -07:00

142 lines
2.6 KiB
JSON

{
"num_speakers": 3,
"speaker_map": {
"HOST": "HOST",
"CO-HOST": "CO-HOST",
"CALLER": "CALLER"
},
"turns": [
{
"speaker": "HOST",
"start": 0.0,
"end": 20.0,
"confidence": 0.88
},
{
"speaker": "CO-HOST",
"start": 15.0,
"end": 25.0,
"confidence": 0.87
},
{
"speaker": "CALLER",
"start": 20.0,
"end": 30.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 25.0,
"end": 430.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 425.0,
"end": 435.0,
"confidence": 0.83
},
{
"speaker": "HOST",
"start": 430.0,
"end": 705.0,
"confidence": 0.85
},
{
"speaker": "CO-HOST",
"start": 700.0,
"end": 710.0,
"confidence": 0.89
},
{
"speaker": "HOST",
"start": 705.0,
"end": 715.0,
"confidence": 0.86
},
{
"speaker": "CALLER",
"start": 710.0,
"end": 720.0,
"confidence": 0.79
},
{
"speaker": "HOST",
"start": 715.0,
"end": 935.0,
"confidence": 0.97
},
{
"speaker": "CALLER",
"start": 930.0,
"end": 945.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 940.0,
"end": 990.0,
"confidence": 0.93
},
{
"speaker": "CALLER",
"start": 985.0,
"end": 995.0,
"confidence": 0.82
},
{
"speaker": "HOST",
"start": 990.0,
"end": 1020.0,
"confidence": 0.9
},
{
"speaker": "CALLER",
"start": 1015.0,
"end": 1030.0,
"confidence": 0.84
},
{
"speaker": "HOST",
"start": 1025.0,
"end": 2120.0,
"confidence": 0.98
},
{
"speaker": "CALLER",
"start": 2115.0,
"end": 2125.0,
"confidence": 0.85
},
{
"speaker": "HOST",
"start": 2120.0,
"end": 2150.0,
"confidence": 0.94
},
{
"speaker": "CO-HOST",
"start": 2145.0,
"end": 2155.0,
"confidence": 0.88
},
{
"speaker": "HOST",
"start": 2150.0,
"end": 2295.0,
"confidence": 0.93
},
{
"speaker": "CALLER",
"start": 2290.0,
"end": 2300.0,
"confidence": 0.8
},
{
"speaker": "HOST",
"start": 2295.0,
"end": 2630.0,
"confidence": 0.97
}
]
}