audiocraft
audiocraft copied to clipboard
facebookresearch
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 mu...
Would be useful to have an easily accessible output folder. Generate forever would help us make many outputs and cherry-pick the best ones. Wildcards could help create unusual and unexpected...
Currently I'm getting okay results, getting a lot of reverb and other audio artifacts, with the below, just looking for some suggestions on what others have found work well. ```...
Hi, since the package is still in a pre-1.0.0 stable release state, maybe it would be worthwhile to push out the 0.0.2 including the already fixed top_p .float bug.
I don't know if it was something from my instalation or if it's the default of the program but here when I press to download the music file it comes...
It would be cool if you could add ```generate_continuation``` for the Gradio app. I was able to hack this together myself by adding a ```gr.Slider``` then modifying the ```predict``` function....
Consider implementing or providing an option to condition a model on a specific audio file, enabling the generation of audio that continues the input audio. I read it's possible using...
Thanks! It's usable the way it is. These are just user interface improvement suggestions. Can these be added? SET SAVE FILE LOCATION Even in the same session in Chrome when...
since torch 2.0 supports MPS it should be possible to make this great project work on Mac
Due to different requirements, a separate webui version was created https://github.com/sdbds/audiocraft-webui Please let me know if there are any problems that need improvement.
 Considered also changing the Gradio widget to prevent negative temp. But I just tried a few samples.... say what you like about the horrible noises you get with negative...
Metadata
Owner
Metadata
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 mu...