vh
5fd69f06b1
The wrapper's `optimized` backend (torch.compile + CUDA graphs + real-time streaming) reads its model registry from a YAML config: default path is ~/qwen3-tts/config.yaml inside the container, which doesn't exist. Without TTS_CONFIG set, the backend boots with an empty registry and every synthesis request fails with "Unknown model key: '<name>'. Available: []". The repo ships /app/config.yaml with all 4 model variants defined. Pointing TTS_CONFIG at it lets the optimized backend load cleanly. This is a prerequisite for benching the optimized backend properly — it's the path to the upstream's claimed 97 ms streaming TTFB. The default `official` backend uses naive HF transformers autoregressive generation that pegged GPU at only 27% utilization and gave us 8-12 s TTFB on bench (no recompile theory needed — same phrase repeated 4x plateaued at 8.5 s, ruling out shape-specific recompilation).
84 lines
3.7 KiB
YAML
84 lines
3.7 KiB
YAML
# Qwen3-TTS — Alibaba's open-weight TTS, deployed via the
|
||
# groxaxo/Qwen3-TTS-Openai-Fastapi wrapper.
|
||
#
|
||
# Why this stack exists alongside cosyvoice: CosyVoice 3 emits
|
||
# Chinese phonemes for non-Chinese inputs (upstream issue
|
||
# FunAudioLLM/CosyVoice#1790, no fix). Qwen3-TTS is from the same
|
||
# Alibaba team but with English first-class — 10 languages, 97 ms
|
||
# streaming TTFB, voice cloning, instruction-driven emotional
|
||
# expression. Released Jan 2026, Apache 2.0.
|
||
#
|
||
# Build: no prebuilt image; pinned to a SHA via docker buildx's git
|
||
# context URL so subsequent rebuilds are reproducible. ~5–10 min on
|
||
# first build (CUDA torch + transformers).
|
||
#
|
||
# Model: 1.7B flagship (~6–8 GB VRAM with bfloat16) by default; the
|
||
# host has plenty of VRAM. Switch to the 0.6B in .env if you ever
|
||
# need more headroom.
|
||
#
|
||
# Voice cloning shape DIFFERS from cosyvoice: profile-based, not
|
||
# voice-id. Profiles live under voice_library/profiles/<name>/ with
|
||
# meta.json + reference.wav, and are referenced as
|
||
# `voice="clone:<name>"` in /v1/audio/speech requests.
|
||
#
|
||
# All tunables live in .env — edit that, not this file.
|
||
|
||
services:
|
||
qwen3-tts:
|
||
image: local/qwen3-tts:${QWEN3_TTS_TAG}
|
||
build:
|
||
context: https://github.com/groxaxo/Qwen3-TTS-Openai-Fastapi.git#${QWEN3_TTS_SHA}
|
||
dockerfile: Dockerfile
|
||
# Upstream Dockerfile defines five stages — without an explicit
|
||
# target, buildkit picks the LAST named stage (`cpu-base`) and
|
||
# produces a CPU-only image with no GPU torch + onnxruntime
|
||
# (not -gpu). Pin to `production` to get the CUDA stack with
|
||
# flash-attn that the model actually needs.
|
||
target: production
|
||
container_name: qwen3-tts
|
||
restart: unless-stopped
|
||
runtime: nvidia
|
||
# Upstream image declares `USER appuser` (uid 1000) but writes
|
||
# state under /root (mode 0700) — appuser can't traverse it, so
|
||
# /v1/voices and any FS-touching endpoint 500s. The model loads
|
||
# only because warmup happens in an early root phase. Pin to root
|
||
# so all paths are reachable. Files written into the host bind
|
||
# mounts become root-owned; that's fine for restic + sudo reads.
|
||
user: "0:0"
|
||
ports:
|
||
- "${QWEN3_TTS_BIND:-0.0.0.0}:${QWEN3_TTS_PORT}:8880"
|
||
environment:
|
||
- NVIDIA_VISIBLE_DEVICES=all
|
||
- PORT=8880
|
||
- TTS_BACKEND=${QWEN3_TTS_BACKEND:-official}
|
||
- TTS_MODEL_NAME=${QWEN3_TTS_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B}
|
||
# Only used when TTS_BACKEND=optimized — points the optimized backend
|
||
# at the upstream config.yaml (which defines the model registry +
|
||
# default model). Without this, the optimized backend looks at
|
||
# ~/qwen3-tts/config.yaml inside the container, which doesn't exist
|
||
# at runtime, leaving the model registry empty and synthesis fails
|
||
# with "Unknown model key".
|
||
- TTS_CONFIG=/app/config.yaml
|
||
- TTS_WARMUP_ON_START=${QWEN3_TTS_WARMUP:-true}
|
||
- TTS_MAX_CONCURRENT=${QWEN3_TTS_MAX_CONCURRENT:-1}
|
||
- ENABLE_VOICE_STUDIO=${QWEN3_TTS_VOICE_STUDIO:-true}
|
||
- VOICE_LIBRARY_DIR=/root/qwen3-tts/voice_library
|
||
- HF_HOME=/root/.cache/huggingface
|
||
volumes:
|
||
- ${QWEN3_TTS_CACHE_DIR}:/root/.cache/huggingface
|
||
- ${QWEN3_TTS_VOICES_DIR}:/root/qwen3-tts/voice_library
|
||
healthcheck:
|
||
test: ["CMD-SHELL", "curl -fsS http://localhost:8880/health >/dev/null || exit 1"]
|
||
interval: 30s
|
||
timeout: 10s
|
||
retries: 3
|
||
# First boot pulls torch + Qwen3-TTS-12Hz-1.7B (~6 GB) and
|
||
# optionally warms the model — give it a generous budget.
|
||
start_period: 600s
|
||
labels:
|
||
- homepage.group=AI Systems
|
||
- homepage.name=Qwen3-TTS
|
||
- homepage.icon=mdi-account-voice
|
||
- homepage.description=Multilingual TTS with English-first emotion (irv-ml1)
|
||
- homepage.href=http://10.100.79.3:${QWEN3_TTS_PORT}
|