Model
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).
Use the NGC CLI to download:
Copied!
| Name | Size | Updated | Actions |
|---|---|---|---|
tts_de_fastpitch_thorstens2102.nemo | 174.78 MB | March 1, 2025 UTC | |
tts_de_fastpitch_thorstens2210.nemo | 174.78 MB | March 1, 2025 UTC | |
tts_de_hifigan_thorstens2102.nemo | 323.51 MB | March 1, 2025 UTC | |
tts_de_hifigan_thorstens2210.nemo | 323.5 MB | March 1, 2025 UTC |