Experimental voice changer model
Total dataset : 310 Mins
[240 Mins of Speech, 60 Mins of Sing, 10 Mins of Non-verb.]
Loops : 212
F0. Rvmpe
Opti. AdamW
Vocoder. HIFIGAN
Embedder. ContentVec

> To enable inference of non-speech sounds or Whisper in the voice changer, please set the index value to 0.

Model Link - https://huggingface.co/SeoulStreamingStation/RVC_Voice_Models/resolve/main/Voice_NELL_V11.zip?download=true

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/SeoulStreamingStation/RVC_Voice_Models/resolve/main/Voice_NELL_V11.zip?download=true Hosted on Hugging Face