hailin 73fd56f30a fix: durable monkey-patch for Speechmatics finalize on flush ... Move the SpeechStream._process_audio patch from container runtime into our own source code so it survives Docker rebuilds. The patch adds client.finalize() on FlushSentinel so EXTERNAL mode produces final transcripts when LiveKit's VAD detects end of speech. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-03-03 02:00:42 -08:00
..
src	fix: durable monkey-patch for Speechmatics finalize on flush	2026-03-03 02:00:42 -08:00
Dockerfile	fix: resolve websockets version conflict and use CPU-only torch	2026-02-28 09:02:31 -08:00
requirements.txt	feat: add STT provider switching (OpenAI ↔ Speechmatics) in settings	2026-03-02 22:13:18 -08:00