Qwen3-tts/docker-compose.yml

services:
  qwen3-tts:
    image: vllm/vllm-omni:latest-aarch64
    container_name: qwen3-tts
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - VLLM_LOGGING_LEVEL=INFO
      - HF_HOME=/root/.cache/huggingface
      # Modelle liegen vollstaendig im Cache → keine Online-Checks gegen huggingface.co.
      # Verhindert Crash "[Errno -3] Temporary failure in name resolution" bei DNS-Ausfall.
      - HF_HUB_OFFLINE=1
      - TRANSFORMERS_OFFLINE=1
      # Keine Lead-in-Stille (war nur Mitigation; Anfangsstottern ist client-seitig).
      # Trailing-Stille bleibt per Default (300ms) gegen abruptes Ende.
      - QWEN3_TTS_LEADIN_SILENCE_MS=0
      - QWEN3_TTS_MODEL=${QWEN3_TTS_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice}
    ports:
      - "8091:8091"
      - "8092:8092"
      - "8094:8094"
    volumes:
      - /home/guru/vllm/data/root:/root
      - ./deploy/qwen3_tts.yaml:/deploy/qwen3_tts.yaml:ro
      - ./docker/entrypoint.sh:/entrypoint.sh:ro
      - ./docker/voice_clone_ui.py:/voice_clone_ui.py:ro
      - ./docker/ws_log_proxy.py:/ws_log_proxy.py:ro
      - ./docker/patch_qwen3_tts_runtime.py:/patch_qwen3_tts_runtime.py:ro
      - ./ui:/ui:ro
    command: ["/bin/bash", "/entrypoint.sh"]
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://localhost:8091/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 120s


  qwen3-tts-clone:
    image: vllm/vllm-omni:latest-aarch64
    container_name: qwen3-tts-clone
    runtime: nvidia
    profiles:
      - clone
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - VLLM_LOGGING_LEVEL=INFO
      - HF_HOME=/root/.cache/huggingface
      - HF_HUB_OFFLINE=1
      - TRANSFORMERS_OFFLINE=1
      - QWEN3_TTS_CLONE_MODEL=${QWEN3_TTS_CLONE_MODEL:-}
      - QWEN3_TTS_CLONE_PORT=8091
    ports:
      - "8091:8091"
    volumes:
      - /home/guru/vllm/data/root:/root
      - ./deploy/qwen3_tts.yaml:/deploy/qwen3_tts.yaml:ro
      - ./deploy/qwen3_tts_clone.yaml:/deploy/qwen3_tts_clone.yaml:ro
      - ./docker/entrypoint_clone.sh:/entrypoint_clone.sh:ro
      - ./docker/patch_qwen3_tts_runtime.py:/patch_qwen3_tts_runtime.py:ro
    command: ["/bin/bash", "/entrypoint_clone.sh"]
    restart: "no"
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://localhost:8091/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 120s