mARTin-B78
295de3059d
- generate_voices.py: scan /config/speakers and /voices recursively, support .ogg and .m4a (M4A auto-converted via ffmpeg), sanitise voice IDs - auto_transcribe.py: scan both host paths recursively, support all formats, use parakeet-asr on port 8010 - docker-compose.yml: mount /home/sparky/Projekte/TTS_Voices/speakers as /voices, add faster-qwen3-tts-voicedesign service on port 8021 - run_voicedesign_server.py: OpenAI-compatible server for VoiceDesign model - voicedesign_voices.json: 8 British/German VoiceDesign voices Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
69 lines
1.8 KiB
YAML
69 lines
1.8 KiB
YAML
services:
|
|
faster-qwen3-tts:
|
|
image: faster-qwen3-tts-dgx-spark:v4
|
|
container_name: faster-qwen3-tts
|
|
restart: unless-stopped
|
|
runtime: nvidia
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=all
|
|
- HF_TOKEN=${HF_TOKEN}
|
|
ports:
|
|
- "8020:8000"
|
|
volumes:
|
|
- /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-Base:/models/Qwen3-TTS:ro
|
|
- /home/sparky/Docker/faster-qwen3-tts/config:/config:rw
|
|
- /home/sparky/Projekte/TTS_Voices/speakers:/voices:ro
|
|
command: >
|
|
/bin/bash -c "
|
|
python3 /config/generate_voices.py &&
|
|
python3 /config/run_server.py
|
|
--model /models/Qwen3-TTS
|
|
--voices /config/voices.json
|
|
--port 8000
|
|
--max-seq-len 2048
|
|
"
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
networks:
|
|
- dgx_net
|
|
|
|
faster-qwen3-tts-voicedesign:
|
|
image: faster-qwen3-tts-dgx-spark:v4
|
|
container_name: faster-qwen3-tts-voicedesign
|
|
restart: unless-stopped
|
|
runtime: nvidia
|
|
environment:
|
|
- NVIDIA_VISIBLE_DEVICES=all
|
|
- HF_TOKEN=${HF_TOKEN}
|
|
ports:
|
|
- "8021:8000"
|
|
volumes:
|
|
- /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-VoiceDesign:/models/Qwen3-TTS-VoiceDesign:ro
|
|
- /home/sparky/Docker/faster-qwen3-tts/config:/config:rw
|
|
command: >
|
|
/bin/bash -c "
|
|
python3 /config/run_voicedesign_server.py
|
|
--model /models/Qwen3-TTS-VoiceDesign
|
|
--voices /config/voicedesign_voices.json
|
|
--port 8000
|
|
--max-seq-len 2048
|
|
"
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
networks:
|
|
- dgx_net
|
|
|
|
networks:
|
|
dgx_net:
|
|
external: true
|