Guilherme
Guilherme
I was testing the MDX23C-8KFFT-InstVoc_HQ on Google Colab, and I was surprised when I heard the result, the audio was slow, the singer was singing slowly and the audio length...
I tested several models, both MDX, MDXC and VR, but the only model that I had results that were actually worse than the UVR GUI was the UVR-DeEcho-DeReverb. Here is...
This PR changes how batch inference works by not reloading the hubert and voice model
This PR is to try to fix the stride warning at the start of the training. Problems: the current solution slows down training and give cuda out of memory. To...
How exactly was he trained? Was there a different configuration used in the training? Because when I and other people tried to train a new model, there was a problem...