Audiogen experiment from facebook AudioCraft

AudioGen generates audio samples based on given descriptions. The follow code block provides instructions for creating a Conda environment and running the script.

module load

 

module load Anaconda3/2022.05 GCCcore/11.3.0 FFmpeg/4.4.2

# Create conda environment

# conda create -n [env_name] conda create -n audioCraft # source activate [env_name] source activate audioCraft # Install required packages conda install pip pip3 install git+https://github.com/facebookresearch/audiocraft.git srun --pty -p gpu --cpus-per-task=12 --gres=gpu:a100:1 --mem=100G bash python3 audio_craft.py

module load Anaconda3/2022.05 GCCcore/11.3.0 FFmpeg/4.4.2 # Create conda environment # conda create -n [env_name] conda create -n audioCraft # source activate [env_name] source activate audioCraft # Install required packages conda install pip pip3 install git+https://github.com/facebookresearch/audiocraft.git srun --pty -p gpu --cpus-per-task=12 --gres=gpu:a100:1 --mem=100G bash python3 audio_craft.py