REQUEST for cleanest vocals

[ybwai]

In the ultimatevocalremovergui repo the recommend approach to get the cleanest vocals is something like:

Take your song (vocals, instrumentals, all of it, the original) and:

1. Run it through UVR5 with the (MDX) Kim Vocals 2 model.
2. Take the vocal output and run THAT through the (VR) de-reverb model.
3. Take the output from that and run it through the (VR) aggressive de-echo model.
4. Take the output from that and run it through a (VR) karaoke model.

Are you supporting or intend to support these capabilities? would be great to have a simple way to chain multiple models back to back via an api.

[MohannadEhabBarakat]

Yes I plan to add pipeline and ensemble features with a very similar interface to the model