cog.yaml

build:
  gpu: true
  python_version: "3.10"
  python_packages:
    - "torch==2.0.1"
    - "numpy==1.24.0"
    - "transformers==4.34.0"
    - "accelerate==0.21.0"
    - "gradio==3.50.2"
    - "fastapi==0.104.0"
    - "uvicorn==0.23.2"
    - "pydantic==2.3.0"
    - "openai-whisper==20231117"
    - "tqdm==4.66.1"
    - "requests==2.31.0"
  system_packages:
    - "wget"
    - "ffmpeg"
    - "libsndfile1"
  run:
    - "pip install -e git+https://github.com/pytorch/fairseq.git#egg=fairseq"
    - "if [ $(uname -m) != 'arm64' ] || [ $(uname -s) != 'Darwin' ]; then pip install flash-attn==2.3.0; fi"
    - "mkdir -p vocoder"
    - "wget https://dl.fbaipublicfiles.com/fairseq/speech_to_speech/vocoder/code_hifigan/mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj/g_00500000 -P vocoder/"
    - "wget https://dl.fbaipublicfiles.com/fairseq/speech_to_speech/vocoder/code_hifigan/mhubert_vp_en_es_fr_it3_400k_layer11_km1000_lj/config.json -P vocoder/"

predict: "predict.py:Predictor"