Tutorials

[NewAgeRipper]

***UPDATE***

Lite-records exclusive! This is a "sequel" sort of speak to the main Multi-Genre model released a few months ago. I haven't released this to my GitHub yet because I'm going to try for even better results and I need to come out with a new accompaniing stacked model.

This is by far the best model I've ever trained up until this point. Please let me know what you all think!

Multi-Genre Model 2 - click here

Do I stick this in the models folder in my vocalremover folder in my docs? Or do I already have this now with the new files I downloaded from the main thread?

[Anjok]

Do I stick this in the models folder in my vocalremover folder in my docs? Or do I already have this now with the new files I downloaded from the main thread?

You'll need to stick into the models folder.

I'm in the process of updating the GUI and releasing new models, so it'll all be bundled together soon.

[NewAgeRipper]

You'll need to stick into the models folder.

I'm in the process of updating the GUI and releasing new models, so it'll all be bundled together soon.

I did and did a test track. Works well. Hopefully something can be trained with Evanescence. There song "Snow White Queen" will not devocal well for some reason.

[chilinvilin]

I did and did a test track. Works well. Hopefully something can be trained with Evanescence. There song "Snow White Queen" will not devocal well for some reason.

Why are you using the gui and not colab? Just curious..

[NewAgeRipper]

Why are you using the gui and not colab? Just curious..

I was running both to see if there was a difference in output. I'm trying to make karaoke versions of all Evanescence that has never been licensed for a karaoke brand yet.

[dimkeal]

Why are you using the gui and not colab? Just curious..

do you feel the collab has better results than the gui?

[Anjok]

do you feel the collab has better results than the gui?

The results will be identical if you're using the same model.