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.
Adding stereo models with left/right codebook interleaving using a variant of the delay pattern. Stereo generation at no extra cost be it at train or inference time.
Adding stereo models with left/right codebook interleaving using a variant of the delay pattern. Stereo generation at no extra cost be it at train or inference time.
Various other improvements to the demos.