Weird because the rest of the stems are gorgeous, the best I've ever heard, and seen on spectral view, so the fact that the vocal stem alone is...
Is "Kim Vocal 2" trained on lossless, and is it a user-selectable/modifiable option?
Well - this model is quite an improvement over htdemucs_ft, with one big problem - the vocal stem sucks! Drum stem makes htdemucs_ft sound like...
SDX 2023 Challenge ends today! If any of the new models can be run locally on your own machine rather than web-upload/process - please advise how!
Hopefully these new models may be incorporated/ported to UVR or some other app or architecture that can be processed on one's local machine rather...
Beautiful, thank you!! So how to actually utilize this model - can I call upon it in Python like a regular demucs model? (ie, demucs -n drumsep...
Thanks for the heads-up on this, how are the results? I cannot get the google collab to work, I keep getting a fatal error: fatal: destination...
Separate names with a comma.
