Pendrokar/xvapitch_nvidia

Model

xVASynth's xVAPitch (v3) type of voice models based on NVIDIA HIFI NeMo datasets.

16 commits

1 linked in READMEs

updated Apr 30, 2025

See the code

README

xVASynth's xVAPitch (v3) type of voice models based on NVIDIA HIFI NeMo datasets.

Models created by Dan Ruta, origin link:

https://www.nexusmods.com/skyrimspecialedition/mods/65022?tab=files

Dataset supposed origin:

https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/stable/core/core.html

Name	Synthesis Sample
ccby_nvidia_hifi_6671_M	Your browser does not support the audio element.
ccby_nvidia_hifi_92_F	Your browser does not support the audio element.
ccby_nvidia_hifi_6097_M	Your browser does not support the audio element.
ccby_nv_hifi_11614_F	Your browser does not support the audio element.
ccby_nvidia_hifi_11697_F	Your browser does not support the audio element.
ccby_nvidia_hifi_12787_F	Your browser does not support the audio element.
ccby_nvidia_hifi_6670_M	Your browser does not support the audio element.
ccby_nvidia_hifi_8051_F	Your browser does not support the audio element.
ccby_nvidia_hifi_9017_M	Your browser does not support the audio element.
ccby_nvidia_hifi_9136_F	Your browser does not support the audio element.

(These audio samples were created with the xVASynth Editor with the SR option (44kHz), not xVATrainer whose automatically created samples often sound different

Legal note: Although these datasets are licensed as CC BY 4.0, the base v3 model that these models are fine-tuned from, was pre-trained on non-permissive data.

v3 base model: https://huggingface.co/Pendrokar/xvapitch

audio

emotion

text-to-speech

Contributors

Pendrokar

16 commits

Similar repos

Pendrokar/xVASynth

Space

DanRuta's xVASynth, GitHub repo: https://github.com/DanRuta/xVA-Synth

nvidia/tts_en_fastpitch

Model

NVIDIA FastPitch (en-US)

Vaibhavs10/open-tts-tracker

1,145

pnnbao-ump/VieNeu-TTS-v3-Turbo

Model

🦜 VieNeu-TTS v3 Turbo

pyp1/VoiceCraft

Model

Repo: https://github.com/jasonppy/VoiceCraft

213

XRXRX/X-Voice

Model

Download Speaking Rate Predictor, X-Voice Stage-1 Model, and X-Voice Stage-2 Model, then place…

bosonai/higgs-tts-3-4b

Model

Higgs TTS 3

773

SWivid/F5-TTS

Model

Download [F5-TTS](https://huggingface.co/SWivid/F5-TTS/tree/main/F5TTS_Base) or [E2…

1,208

Linked in READMEs

Vaibhavs10/open-tts-tracker

1,145

README badge

Pendrokar/xvapitch_nvidia

Model

xVASynth's xVAPitch (v3) type of voice models based on NVIDIA HIFI NeMo datasets.

16 commits

1 linked in READMEs

updated Apr 30, 2025

See the code

README

xVASynth's xVAPitch (v3) type of voice models based on NVIDIA HIFI NeMo datasets.

Models created by Dan Ruta, origin link:

https://www.nexusmods.com/skyrimspecialedition/mods/65022?tab=files

Dataset supposed origin:

https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/stable/core/core.html

Name	Synthesis Sample
ccby_nvidia_hifi_6671_M	Your browser does not support the audio element.
ccby_nvidia_hifi_92_F	Your browser does not support the audio element.
ccby_nvidia_hifi_6097_M	Your browser does not support the audio element.
ccby_nv_hifi_11614_F	Your browser does not support the audio element.
ccby_nvidia_hifi_11697_F	Your browser does not support the audio element.
ccby_nvidia_hifi_12787_F	Your browser does not support the audio element.
ccby_nvidia_hifi_6670_M	Your browser does not support the audio element.
ccby_nvidia_hifi_8051_F	Your browser does not support the audio element.
ccby_nvidia_hifi_9017_M	Your browser does not support the audio element.
ccby_nvidia_hifi_9136_F	Your browser does not support the audio element.

(These audio samples were created with the xVASynth Editor with the SR option (44kHz), not xVATrainer whose automatically created samples often sound different

Legal note: Although these datasets are licensed as CC BY 4.0, the base v3 model that these models are fine-tuned from, was pre-trained on non-permissive data.

v3 base model: https://huggingface.co/Pendrokar/xvapitch

audio

emotion

text-to-speech