NVIDIA
NVIDIA
TTS DE Multi-Speaker FastPitch HiFiGAN
Model
NVIDIA
NVIDIA
TTS DE Multi-Speaker FastPitch HiFiGAN

This collection includes two German models: FastPitch trained on the HUI-Audio-Corpus-German clean dataset where the 5-largest amount of speakers are selected and balanced; HiFiGAN is trained on mel-spectrograms predicted by the Multi-speaker FastPitch.

NeMo - Text to Speech
This collection contains NeMo models for Text to Speech (TTS)