Ok yeah I had a look at that earlier yesterday but I didn't see where you can change model to model B or A, I'll give it another look though. Thanks for the reply btw..
Is there any trainable models being developed to strictly make high quality vocal extractions from a song? Seems the vocal isolating technology still has a long ways to go to catch up to vocal removing.
Is there any trainable models being developed to strictly make high quality vocal extractions from a song? Seems the vocal isolating technology still has a long ways to go to catch up to vocal removing.
There is a guide on how to train a model on the GitHub page. They have also listed the sources of music they used to train the default models