javis-bot b17961e9e3 feat(tts): add MeloTTS Korean voice via warm worker with offline-baked cache ...

Adds a dedicated MeloTTS Korean voice (speed 1.5) as the primary TTS engine,
served by a long-lived in-container worker so each Discord turn pays only
inference cost, not model-load cost.

- bridge/melo_worker.py: tiny HTTP service in its own /opt/melo py3.11 venv,
  keeps the KR model warm, returns PCM16 WAV on POST /synth.
- bridge/server.py: synthesize() routes to the melo worker first; Piper stays
  as an opt-in fallback (MELO_FALLBACK_PIPER, default off so Korean is never
  mangled through the English voice). /health reports tts_engine.
- docker/setup-melo.sh: builds the isolated venv (pinned torch 2.12.0 /
  torchaudio 2.11.0 CPU, MeloTTS pinned to a commit for reproducible rebuilds),
  pre-fetches mecab-ko, and warms a dedicated HF cache (/opt/melo-cache) with a
  real KR synth so all BERT + KR checkpoint assets are baked into the image.
- docker/supervisord.conf: runs melo-worker before the bridge with
  HF_HOME=/opt/melo-cache (the whisper_cache volume shadows the default HF
  cache) plus HF_HUB_OFFLINE/TRANSFORMERS_OFFLINE so it reads the baked cache
  and never retries the network on load.
- Dockerfile/.env.example: wire the melo build layer and config knobs.

Verified: offline synth passes with --network none and the prod volume mounted;
prod container recreated, all supervisord services up, bot logged in, and an
end-to-end /tts call returns a 44.1kHz mono PCM16 WAV.

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

2026-06-12 19:01:54 +09:00

6.6 KiB

Raw Blame History

View Raw