Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
MIT License
20.18k
stars
2.01k
forks
source link
Can I load the melody's model in 8 bits in order to reduce the memory used on the GPU, as in NLP language model? #333
My GPU memory is too small, but I want to loaded this model locally!