javis-bot 7da2fcb5e5 feat(stt): beam-search decoding + no prev-text conditioning for accuracy ...

Whisper was decoding with beam_size=1 (greedy), the least accurate setting,
which hurt recognition on short/accented/noisy Discord-mic speech. Switch the
default to beam search (5, Whisper's own default) and stop conditioning on the
previous clip's transcript (which causes repetition/drift on isolated short
utterances rather than helping). Both are env-tunable (STT_BEAM_SIZE,
STT_CONDITION_ON_PREV) so accuracy/latency can be traded without a code change;
wired into docker-compose and documented in .env.example.

2026-06-24 17:55:20 +09:00

31 KiB

Raw Blame History

View Raw