Description
This is a model based on the French Narrator from SpongeBob trained on RVC using the crepe method. This was trained locally and is my first model trained to 2K Epochs. This was trained on around 10-12 minutes of audio. This is ideally good for a regular talking voice, not tested with singing. Sounds pretty accurate.
Comments
This is what this is based on. If it wasn't obvious lol.
Video removed in response to copyright claim.
Test regular speaking audio with the model:
Narrator (SpongeBob SquarePants) RVC 2K Epochs [42K Steps]
SpongeBob FrenchPants Now we got different language Spongebobs Do Spanish and Arabic next
Did a music test with Ice Spice Munch, complete aids.
you thought i was feeling you that .. a MUUUGHGHHGHG
but its good
yeah, I used the music video audio so there was a non-song part that glitched tf out, I find it funny tho.
Next one ima make is squidward tennis balls
ooooo
nice
I WANT SOME CHEESEBURGERS JUST TO EAT!
Welp, new RVC update broke this model as well.
I'll retrain it soon!
local chads stay winnin
Narrator (SpongeBob SquarePants) RVC 2K Epochs [52K Steps]
Alright, the model is updated and retrained on RVC crepe and should work with RVC for inferences again, please let me know if it works on your end guys! I'll post at least a couple new samples on the retrained model. It has a higher step count than before as well at the same epoch count of 2K epoch.
Narrator sings Amish Paradise By Weird Al (new crepe model update)
And a dead forced meme.
I AM A SURGEON!! (Good Doctor Sample)
I AM A SURGEON (just the meme, fixed)
I can’t download it, it says it@s downloaded by to menny people
You can find it here.
Thanks
Add a comment
Samples
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
Weekly Metrics
More to explore
Loading more