xVASynth's xVAPitch (v3) type of voice models based on NVIDIA HIFI NeMo datasets.
Models created by Dan Ruta, origin link:
Dataset supposed origin:
ccby_nvidia_hifi_6671_M:
ccby_nvidia_hifi_92_F:
ccby_nv_hifi_11614_F:
ccby_nvidia_hifi_11697_F:
ccby_nvidia_hifi_12787_F:
ccby_nvidia_hifi_6097_M:
ccby_nvidia_hifi_6670_M:
ccby_nvidia_hifi_8051_F:
ccby_nvidia_hifi_9017_M:
ccby_nvidia_hifi_9136_F:
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
Model tree for Pendrokar/xvapitch_nvidia
Base model
Pendrokar/xvapitch