Quote Originally Posted by NewAgeRipper View Post
OK, so I've been playing with the new beta release just posted and I'm finding that the vocal removal isn't quite on par with the current Google Colab results. I tried all 3 models and it appears that for the song I already have done using the Google Colab method, I don't really hear any improvement differences. That's not saying it's useless. It's saying I will have to mess with another track to hear for sure that Google Colab can't currently do yet. It will probably have to be when the final release is finished.
Sorry, it's been hard squeezing in time to update this thread. Have you been setting the sr and hop length accordingly based on the model you're using?