ConsistencyVC/ConsistencyVC-voive-conversion

Is hifigan vocoder really used?

Closed this issue · 1 comments

There's mention of the HifiGan vocoder in the description , but I don't see any reference in the code (except for utils.py, but those are leftovers from the FreeVC).

The model's decoder part is similar to the generator part of the HifiGAN. Actually VITS's decoder is referred to HifiGAN, FreeVC is referred to VITS, and ConsistencyVC is referred to FreeVC.