NVIDIA
NVIDIA
TTS Zh Fastpitch HifiGan SFSpeech
Model
NVIDIA
NVIDIA
TTS Zh Fastpitch HifiGan SFSpeech

This model card includes two Mandarin Chinese models: 1) FastPitch Mel-spectrogram generator trained on SF Chinese/English Bilingual Speech dataset; 2) HiFiGAN vocoder trained on Mel-spectrograms predicted by the FastPitch.

NameSizeUpdatedActions
tts_zh_fastpitch_sfspeech.nemo
174.81 MBMarch 1, 2025 UTC
tts_zh_hifigan_sfspeech.nemo
323.5 MBMarch 1, 2025 UTC