EJClaw 8539acd0f8 feat(stt/voice): better recognition, sustained barge-in, fragment discard ...

STT (whisper_worker): add VAD tuning (speech_pad_ms so soft first/last words
aren't clipped), condition_on_previous_text=False + temperature fallback +
no_speech/logprob/compression thresholds to reject noisy/quiet decodes, drop
per-segment non-speech, and a hallucination guard that blanks Whisper's classic
Korean silence/noise boilerplate ("감사합니다" 등) when no_speech_prob is high.

Barge-in (bot.mjs): stop the bot's TTS only when the speaking (green ring) stays
on for >= WSAI_BARGE_IN_MS (default 700ms), not on the first blip — cancelled if
speaking stops in time. AfterSilence 800->1000ms so trailing soft words finish.

Fragment gate (dashboard): a lone connective filler ("그러면") carries no
answerable intent -> discard as [대기] instead of replying; hidden by the noise
filter like [잡음].

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-08-27 02:13:50 +09:00

95 KiB

Raw Blame History

View Raw