25 lines
952 B
YAML
25 lines
952 B
YAML
# Configuration for Cog ⚙️
|
|
# Reference: https://github.com/replicate/cog/blob/main/docs/yaml.md
|
|
|
|
build:
|
|
gpu: true
|
|
system_packages:
|
|
- libgl1-mesa-glx
|
|
- libglib2.0-0
|
|
- ffmpeg
|
|
- espeak-ng
|
|
python_version: "3.11"
|
|
python_packages:
|
|
- torch==2.1.0
|
|
- torchaudio==2.1.0
|
|
- xformers
|
|
- phonemizer==3.2.1
|
|
- whisperx==3.1.1
|
|
- openai-whisper>=20231117
|
|
run:
|
|
- git clone https://github.com/facebookresearch/audiocraft && pip install -e ./audiocraft
|
|
- pip install "pydantic<2.0.0"
|
|
- curl -o /usr/local/bin/pget -L "https://github.com/replicate/pget/releases/download/v0.6.0/pget_linux_x86_64" && chmod +x /usr/local/bin/pget
|
|
- mkdir -p /root/.cache/torch/hub/checkpoints/ && wget --output-document "/root/.cache/torch/hub/checkpoints/wav2vec2_fairseq_base_ls960_asr_ls960.pth" "https://download.pytorch.org/torchaudio/models/wav2vec2_fairseq_base_ls960_asr_ls960.pth"
|
|
predict: "predict.py:Predictor"
|