Facebook Research AudioCraft Ships JASCO Text-to-Music Model Under CC-BY-NC 4.0
Summary
Facebook Research's AudioCraft library ships MusicGen, AudioGen, EnCodec, and the JASCO text-to-music model, which conditions on chords, melodies, and drums. The code runs on Python 3.9 and PyTorch 2.1.0 and carries an MIT license, while model weights fall under CC-BY-NC 4.0. The repository lists 23.7k stars.
Key Points
- GitHub lists 2.7k forks of the facebookresearch/audiocraft repository.
- The project FAQ states AudioCraft ships training code for its models.
- Users override the model cache location by setting the AUDIOCRAFT_CACHE_DIR environment variable.