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.
Out of all the MusicGen samples I've heard so far, only one actually finished the song without getting cut off. How is this achieved? I'd like to generate a song with a clear ending.
Out of all the MusicGen samples I've heard so far, only one actually finished the song without getting cut off. How is this achieved? I'd like to generate a song with a clear ending.