services:
  transcribe:
    build: .
    ports:
      - "8000:8000"
    restart: always
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    environment:
      - WHISPER_MODEL=large-v3-turbo
      - WHISPER_DEVICE=cuda
      - WHISPER_COMPUTE_TYPE=float16