Michael Stevens (VSauce)

Create

Michael Stevens (VSauce)

RVC v2E-Celeb
3m377 user image
3m377
2 years ago
👀

433

👍

8

🪄

85

Description

Trained using his video "Why Are Bad Words Bad?" (around 9 minutes of data) 48k sample rate, mangio-crepe Please do credit me (@iam3m377 on youtube), I'd love to see what people do with my models

Comments

3m377 user image
3m377
2 years ago

here's your sample (japanese)

3m377 user image
3m377
2 years ago

will send english sample in a minute or two

3m377 user image
3m377
2 years ago

english sample

3m377 user image
3m377
2 years ago

this was a stress test, just wanted to see if it could hit high notes

trbharry user image
trbharry
2 years ago

why the voice is girlish of vsauce<:skullsob:1093200088261734420>

StakenS user image
StakenS
2 years ago

hey, vsauce, michael here, where are your gpu's?

3m377 user image
3m377
2 years ago

v2 coming soon...

3m377 user image
3m377
2 years ago

https://huggingface.co/3m377/VSauceMichaelV2/resolve/main/VSauceMichaelV2.zip vsauce v2 same dataset except I put it through adobe enhance 600 epochs rmvpe 48k sample rate

3m377 user image
3m377
2 years ago

Michael Stevens (VSauce) RVC V2 600 Epochs

3m377 user image
3m377
2 years ago

sample soon

3m377 user image
3m377
2 years ago

big iron

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

More to explore

Loading more

Selected Audio
Selected Audio