NVIDIA
NVIDIA
RIVA EnglishUS Hifigan
Model
NVIDIA
NVIDIA
RIVA EnglishUS Hifigan

HifiGAN is a neural vocoder model for text-to-speech applications. It is intended as the second part of a two-stage speech synthesis pipeline, with a mel-spectrogram generator such as FastPitch as the first stage.

Sign in to see Related Collections for this ModelSigning in will also allow download accessSign In
Riva Speech Skills
Collection of common Riva Speech Skills resources.