devNegative-asm
Results
13
comments of
devNegative-asm
Ok, I think I figured it out. the pitch slider on UI (or `trans` from the inference script) needs to bring the input voice to well within the vocal range...
I think it's the discriminator part of the GAN. necessary for training, but not for inference
make sure the cuda version used by torch is the same as the cuda drivers you have installed