Link - https://huggingface.co/Freaky98/CatNap-rvc-v2-120e/resolve/main/CatNap-rvc-v2-120e.zip?download=true

A 41-minute lossless dataset. This isn't the official CatNap voice, but a recreation I made. For the voice, I used an old whispering TTS. First, I formant-shifted the voice (using Melodyne), then slowed it down, applied interpolation, and bit-crushed it. I also EQ'd it to match the original CatNap voice. As for the noise in the voice, it's part of the voice when there is actual silence; it's clean. Sampled at 20k.

The model also works great with real-time voice changer.

This model is not meant for singing!

Fun fact: I actually spend more time making the thumbnail than the model. I really hate Blender sometimes.

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/Freaky98/CatNap-rvc-v2-120e/resolve/main/CatNap-rvc-v2-120e.zip?download=true