search

facebookresearch / audiocraft

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
20.7k stars 2.11k forks source link

Train without text condition? #309

Open a624090359 opened 11 months ago

a624090359 commented 11 months ago

I want train this model without label just music. What can I do to input the music into the model so that the music is generated in a style similar to the music I input? Deleting some files or modifying which configuration files?

jmren168 commented 11 months ago

Try to find some music annotation tool? Then you will get annotations. Finally, you could train using pair of annotations and music.