acdf098c41
Mirrors the ASR backend pattern exactly: a BACKENDS dict in
tts/router.py maps a backend name to its worker URL, so adding the
next backend is just a new worker file + venv + supervisord entry +
one dict line. XTTS-v2 runs in its own venv (--system-site-packages,
inherits base image torch/CUDA) as a new supervisord program on
port 8005.
XTTS is zero-shot voice cloning, so a reference-voice library was
added (/tts/voices CRUD, stored under /srv/tts/voices) — synthesis
requires picking a previously uploaded voice. Results and model
cache live under /srv/tts/{results,models-cache}, new quadlet
volumes, owned by the same 983:983 user as the existing /srv/asr
dirs.
Fixed two environment issues uncovered while getting XTTS to
actually run inside the container (non-root user, root-built venvs):
- coqui-tts only pins transformers>=4.57 with no ceiling, so pip
installed an incompatible 5.x; pinned to the last 4.x release.
- HOME defaults to /app (owned by root) for the container's runtime
user, so numba/matplotlib/torch cache writes failed; HOME is now
forced to /tmp in all three workers (faster_whisper, qwen3, xtts)
before any of those libraries get imported.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
21 lines
664 B
Python
21 lines
664 B
Python
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
|
|
from core.config import env_str
|
|
|
|
TTS_BASE_DIR = Path(env_str("TTS_BASE_DIR", "/srv/tts"))
|
|
TTS_MODEL_CACHE = Path(env_str("TTS_MODEL_CACHE_DIR", str(TTS_BASE_DIR / "models-cache")))
|
|
TTS_VOICE_DIR = TTS_BASE_DIR / "voices"
|
|
TTS_RESULT_DIR = TTS_BASE_DIR / "results"
|
|
|
|
DEFAULT_TTS_BACKEND = env_str("DEFAULT_TTS_BACKEND", "xtts")
|
|
DEFAULT_TTS_LANGUAGE = env_str("DEFAULT_TTS_LANGUAGE", "ko")
|
|
|
|
XTTS_URL = env_str("XTTS_URL", "http://127.0.0.1:8005")
|
|
|
|
|
|
def ensure_runtime_dirs() -> None:
|
|
for p in [TTS_BASE_DIR, TTS_MODEL_CACHE, TTS_VOICE_DIR, TTS_RESULT_DIR]:
|
|
p.mkdir(parents=True, exist_ok=True)
|