Description
This is an RVC model trained using the experimental crepe method, however it should work regardless of what fork of RVC you are on. This model was trained on around 12 minutes of audio samples from the TV show. This model sounds good for only 4 hours of training. Should work for regular vocals and singing.
Comments
ell0er
Here's an audio inference using audio from the show that wasn't in my dataset.
ell0er
I'll post a song later, 😉
ell0er
(Also I'm gonna retrain a couple of my old voices soon on crepe)
ell0er
Campfire song covered by Patchy.
ell0er
Got em.
ell0er
Patchy (SpongeBob) RVC 1K Epochs [36K Steps]
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
