Description
woohoo the ceo of phase connect ai model yeah baby we're rollin trained on 11 and a half minutes of him speaking from jelly's ama stream pitch extraction: rmvpe steps: 18k(?) batch size: 7 pretrain: regular v2 / 32k huggingface:
Comments
sxndypz
samples soon
sxndypz
i think
sxndypz
the sample's a bit broken because of the acapella but this will do.
Leo_Frixi
In some parts it sounds authentic but in some other parts it got artifacting.
sxndypz
the dataset's a bit scuffed
Leo_Frixi
🐟
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