Added training to my WebUI, help needed with testing if it works

[1aienthusiast]

First things first, I want to thank You for all the contributions You've done to the open source community!

I've implemented this repo in my MusicGen WebUI, but I need help with testing if it works (I have a 12GB card and I can only get up to 2 epochs, because of that the resulting songs don't sound very good so I'm not sure if I'm doing something wrong), I'm wondering if anyone could upload a finetuned model to HuggingFace or test it in the WebUI.

Again, thanks for all the contributions You've done and thanks for the MusicGen trainer!