Revert "feat: replace MeloTTS with Coqui XTTS-v2 natural Korean voice"
Some checks failed
Release / semantic-release (push) Successful in 35s
tests / Unit tests (Linux, Python 3.11) (push) Failing after 5m16s
Release / build-windows (push) Has been cancelled
Release / build-macos (arm64, macos-latest) (push) Has been cancelled
Release / build-macos (x64, macos-15-intel) (push) Has been cancelled
Release / release-main (push) Has been cancelled
Release / release-develop (push) Has been cancelled
Release / build-linux (push) Has been cancelled

This reverts commit 39a0944105.
This commit is contained in:
javis-bot
2026-06-23 03:15:54 +09:00
parent 39a0944105
commit 7ad5d99380
11 changed files with 243 additions and 251 deletions

View File

@@ -49,22 +49,25 @@ stdout_logfile_maxbytes=0
stderr_logfile=/dev/stderr
stderr_logfile_maxbytes=0
[program:xtts-worker]
; Warm Coqui XTTS-v2 Korean voice (natural female "Ana Florence") in its own
; py3.11 venv. The bridge's synthesize() POSTs here; if this is down the bridge
; falls back to Piper (English) only when XTTS_FALLBACK_PIPER=1.
command=/app/docker/run-if-role.sh full,bot /opt/xtts/bin/python /app/bridge/xtts_worker.py
[program:melo-worker]
; Warm MeloTTS Korean voice (speed 1.5) in its own py3.11 venv. The bridge's
; synthesize() POSTs here; if this is down the bridge falls back to Piper.
command=/app/docker/run-if-role.sh full,bot /opt/melo/bin/python /app/bridge/melo_worker.py
directory=/app
; TTS_HOME points at the dedicated, image-baked XTTS cache (warmed in
; setup-xtts.sh). The brain's whisper_cache volume is mounted over
; /root/.cache, so a dedicated non-volume cache dir avoids the baked model being
; shadowed and re-downloaded (which would fail if the host is offline).
; XTTS_DEVICE / XTTS_SPEAKER / XTTS_LANGUAGE inherit from the container env
; (compose sets them with defaults: cuda / "Ana Florence" / ko). supervisord
; interpolates %(ENV_x)s from its own environment, which is the container's — so
; these must always be set in the env (compose guarantees it) or this expansion
; fails at startup. COQUI_TOS_AGREED accepts the non-commercial XTTS license.
environment=XTTS_DEVICE="%(ENV_XTTS_DEVICE)s",XTTS_SPEAKER="%(ENV_XTTS_SPEAKER)s",XTTS_LANGUAGE="%(ENV_XTTS_LANGUAGE)s",XTTS_WORKER_HOST="127.0.0.1",XTTS_WORKER_PORT="8771",TTS_HOME="/opt/xtts-cache",COQUI_TOS_AGREED="1"
; HF_HOME points at the dedicated, image-baked melo cache (warmed in
; setup-melo.sh). The brain's whisper_cache volume is mounted over
; /root/.cache/huggingface, so without this the pre-cached BERT + KR checkpoint
; would be shadowed and re-downloaded (and would fail if the host is offline).
; HF_HUB_OFFLINE/TRANSFORMERS_OFFLINE force pure-cache reads: the pinned old
; transformers/huggingface_hub otherwise retry the network on every load and
; error out instead of falling back to the (complete) baked cache.
; MELO_DEVICE and MELO_SPEED inherit from the container env (compose sets both
; with defaults: cuda / 1.5) so the worker runs MeloTTS on the GPU at the
; configured rate. supervisord interpolates %(ENV_x)s from its own environment,
; which is the container's — so MELO_SPEED must always be set in the env
; (compose guarantees it) or this expansion fails at startup. Hardcoding 1.5
; here previously shadowed the .env value, so lowering MELO_SPEED had no effect.
environment=MELO_LANGUAGE="KR",MELO_SPEED="%(ENV_MELO_SPEED)s",MELO_DEVICE="%(ENV_MELO_DEVICE)s",MELO_WORKER_HOST="127.0.0.1",MELO_WORKER_PORT="8770",HF_HOME="/opt/melo-cache",HF_HUB_OFFLINE="1",TRANSFORMERS_OFFLINE="1"
priority=280
autorestart=true
stdout_logfile=/dev/stdout