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.
Hello! I’m trying to use MusicGen to generate samples for music production. I wonder whether there's any pre-determined pattern for the output's starting position between two beats. Is there any way to engineer the prompt (just like how we specify the desired BPM) so that the output audio starts exactly on beat?
Hello! I’m trying to use MusicGen to generate samples for music production. I wonder whether there's any pre-determined pattern for the output's starting position between two beats. Is there any way to engineer the prompt (just like how we specify the desired BPM) so that the output audio starts exactly on beat?