azcomputerguru/claudetools
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
594 Commits 3 Branches 0 Tags
46bd5fc2f7006aecaa8b73a6ee460a4609f16f75
Commit Graph

3 Commits

Author SHA1 Message Date
Mike Swanson
488bf5849e radio: attach caller names to Q&A pairs from transcript intros 
QAPair gets caller_name and caller_role fields populated by a new
attach_caller_names(pairs, transcript_segments) helper. For each pair,
finds the active opening intro at the question_start time (8s forward
tolerance, no backward limit — a caller's call can run for 10+ minutes
and the intro happens once at the start) and attaches the speaker name.

Validation on 9-episode test set:
  19/19 Q&A pairs (100%) now have caller names attached.

Examples of corrections from oracle attribution:
  2018-s10e18 @ 73:36  Christopher (was misattributed to "Tara")
  2015-s7e19 @ 35:45   William     (was misattributed to "Tara")
  2010-05-08-hr1       Jackie x3, Bruce
  2012-03-10-hr1       Adam x2
  2016-s8e43           John, Doug
  2017-s9e30           Tom, Denise x3, Charlie

speaker_oracle.py: adds speaker_at(time, intros) helper used both by the
existing resolve_speakers() and the new caller-name attachment. Also
adds the "let's fit/bring/put X in/on" intro pattern variant (caught
Charlie at 70:21 in 2017-s9e30 that "talk to X" missed).

download_full_archive.py: SSH keepalive every 30s + per-file retry-on-
failure (up to 3 attempts with reconnect). Earlier run hung on a dead
connection at file 109 of 589 with no recovery; restarted run is now
running at ~10 MB/s vs ~2-3 MB/s before.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-27 16:55:31 -07:00
Mike Swanson
e9ac607500 radio show: co-host voice profile, Q&A extraction fixes, archive index 
- Build Tom (co-host) voice profile (44 embeddings, 0.698 similarity to Mike)
- diarizer.py: add CO-HOST speaker label for cohost-role profiles
- voice_profiler.py: emit "Cohost: <name>" label for cohost role
- qa_extractor.py: overlap resolution at load time (midpoint boundary split),
  4s CALLER-preference threshold, turn-based caller-intro lookback (2 HOST turns),
  _preceded_by_caller_intro() helper, _PHONE_GREETING pattern,
  751-1041 + "we'll get your problem solved" promo signatures
- benchmark.py: use src.transcriber.transcribe with batch_size=16
- add index_test_episodes.py and build_cohost_profile.py scripts
- add .gitignore (exclude episodes, transcripts, *.db, .venv)
- session log: 2026-04-27-qa-extraction-cohost-indexing.md

Result: 2016-s8e43 drops from 12 false-positive Q&A pairs to 2 real caller pairs.
archive.db: 6 episodes, 762 segments, 10 Q&A pairs, FTS5 search verified.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-04-27 14:41:04 -07:00
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