Marius Mutu
ce273d14db
Gemma 4 cloud audio was infeasible (31b-cloud has no audio; E4B broken upstream, no deploy host), so improve faster-whisper instead. - Pin temperature=0.0 to disable the fallback ladder that re-decoded unclear audio up to 6x (source of the 16-24s latency outliers); reject hallucinated segments via avg_logprob/compression_ratio in the new pure _filter_segments. - Adopt mikr/whisper-small-ro-cv11 (CT2 int8) via configurable voice.stt_model: spike showed WER 24%->10%, numbers fixed at source, +0.33s p50 (in budget). - Add tools/voice_stt_mine.py (log mining) + tools/voice_stt_spike.py (model eval with diacritic scoring) + tests for the gate and miner. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
33 lines
422 B
Plaintext
33 lines
422 B
Plaintext
.venv/
|
|
venv/
|
|
__pycache__/
|
|
*.pyc
|
|
*.pyo
|
|
*.egg-info/
|
|
sessions/
|
|
logs/
|
|
memory/*
|
|
!memory/kb/
|
|
memory/kb/*.sqlite
|
|
*.sqlite
|
|
.env
|
|
*.secret
|
|
.DS_Store
|
|
*.swp
|
|
bridge/whatsapp/node_modules/
|
|
bridge/whatsapp/auth/
|
|
.vscode/
|
|
.idea/
|
|
credentials/
|
|
.claude/
|
|
*.pid
|
|
memory.bak/
|
|
.use_openrouter
|
|
.gstack/
|
|
|
|
# Runtime state — auto-modified by dashboard/cron/heartbeat
|
|
approved-tasks.json
|
|
dashboard/status.json
|
|
tools/anaf-monitor/monitor.log
|
|
models/
|