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
20.19k stars 2.02k forks source link

Music inpainting? #134

Open jhurliman opened 1 year ago

jhurliman commented 1 year ago

I see this repository has code for extending an audio clip, conditioned on the input audio. Would it be possible to fill in a missing segment, conditioned on both the beginning and end input audio?

r9k commented 1 year ago

The same technique could be used to make audio loops.

starktyping commented 9 months ago

I see this repository has code for extending an audio clip, conditioned on the input audio. Would it be possible to fill in a missing segment, conditioned on both the beginning and end input audio?

@jhurliman Did you find out a way to do this? I am trying to do this and would like to know if it has been done before I go digging into the model to try and implement it myself. Would the model have to be trained or at least fine-tuned for this specific task?