services:
  speaches:
    image: ghcr.io/speaches-ai/speaches:latest-cuda
    container_name: voicecoach-speaches-gpu
    restart: unless-stopped
    environment:
      - WHISPER__INFERENCE_DEVICE=cuda
      - WHISPER__COMPUTE_TYPE=float16
      - WHISPER__TTL=-1
    volumes:
      - speaches-models:/home/ubuntu/.cache
    ports:
      - "8000:8000"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    labels:
      - "com.centurylinklabs.watchtower.enable=false"
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 180s
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "3"

volumes:
  speaches-models: