Description
this model is mainly trained on red vox vocals
Comments
yeey5
Vinny (Red Vox/Vinesauce) (RVC V2) 500 Epochs
FunnyDannyG
yo
FunnyDannyG
singing binyot
yeey5
Vinny (Red Vox/Vinesauce) (RVC V2) 250 & 500 Epochs
yeey5
New model can talk
FunnyDannyG
Sounds good and slightly different from my speaking Vinny
FunnyDannyG
Nice work
FunnyDannyG
What was your dataset like
FunnyDannyG
Mine was mostly streams from 2022 that I had to remove all the background noise from
yeey5
i found 13 minutes of talking without any background noise
FunnyDannyG
Oh I just used RX Pro and UVR to isolate about 30 minutes of audio from some 2022 streams
Add a comment
Samples
New
Classic
1. Singing
Male
English
2. Singing
Female
English
3. Singing (Dry)
Female
English
4. Singing (High)
Female
English
5. Singing 2
Male
English
6. Singing (Dry)
Male
English
7. Singing (Dry, High)
Male
English
Pitch
![WENDY of Red Velvet [Alt Ver.]](https://assets.weights.com/clm72stnt0pwicctctj412tw8/e7cf9ccf81deb61dce6d37bcfaec5067.gif)
![Mario Judah (Whole Lotta Red) ]](https://imgproxy.weights.com/insecure/size:860:0/resizing_type:fill/plain/https://assets.weights.com/clm72kf3w00rlcctc0m9ozw58/793caea01a65a897526488f7f3be4252.png)
![Totally Serious MCM/FNF Red Mist Squidward [PlacidPigeon]](https://imgproxy.weights.com/insecure/size:860:0/resizing_type:fill/plain/https://assets.weights.com/clm72od1c0e4gcctcf7w7a25h/71a9942d322f4441136ec7eb22592b08.jpg)
