mARTin
60db1b181f
Run Qwen3-TTS with CUDA graph acceleration on NVIDIA DGX Spark (ARM64 / SM 121 / CUDA 13) as an OpenAI-compatible TTS API server. - Dockerfile targeting nvidia/cuda:13.0.2-base-ubuntu24.04 with ARM64 cu130 PyTorch wheels - Patch for max-seq-len support to handle long reference audio without crashes - OpenWebUI + SillyTavern compatible API endpoints (/v1/models, /v1/audio/voices, /speakers) - Voice management: auto-generate voices.json from speaker reference audio files - Auto-transcription helper script for generating reference text from audio Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
41 lines
1.1 KiB
YAML
41 lines
1.1 KiB
YAML
services:
|
|
faster-qwen3-tts:
|
|
image: martinb78/faster-qwen3-tts-dgx-spark:latest
|
|
container_name: faster-qwen3-tts
|
|
restart: unless-stopped
|
|
runtime: nvidia
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=all
|
|
# Optional: set HF_TOKEN if model needs downloading from HuggingFace
|
|
# - HF_TOKEN=${HF_TOKEN}
|
|
ports:
|
|
- "8020:8000"
|
|
volumes:
|
|
# Mount your local Qwen3-TTS model (download first, see README)
|
|
- ${MODEL_PATH:-./models/Qwen3-TTS}:/models/Qwen3-TTS:ro
|
|
# Config directory (voices.json generated on startup)
|
|
- ./config:/config:rw
|
|
# Speaker reference audio files
|
|
- ./config/speakers:/voices:ro
|
|
command: >
|
|
/bin/bash -c "
|
|
python3 /config/generate_voices.py &&
|
|
python3 /config/run_server.py
|
|
--model /models/Qwen3-TTS
|
|
--voices /config/voices.json
|
|
--port 8000
|
|
"
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
networks:
|
|
- dgx_net
|
|
|
|
networks:
|
|
dgx_net:
|
|
external: true
|