NVIDIA
NVIDIA
TTS De FastPitch HiFi-GAN
Model
NVIDIA
NVIDIA
TTS De FastPitch HiFi-GAN

This collection contains two models: 1) FastPitch (around 50M parameters) trained on OpenSLR neutral German dataset with over 23 hours of German speech and 1 speaker. 2) HiFi-GAN trained on mel spectrograms produced by the FastPitch model in (1).

NameSizeUpdatedActions
tts_de_fastpitch_thorstens2102.nemo
174.78 MBMarch 1, 2025 UTC
tts_de_fastpitch_thorstens2210.nemo
174.78 MBMarch 1, 2025 UTC
tts_de_hifigan_thorstens2102.nemo
323.51 MBMarch 1, 2025 UTC
tts_de_hifigan_thorstens2210.nemo
323.5 MBMarch 1, 2025 UTC