Description
Origin: Hololive minutes and 53 seconds of Sora talking Batch size per GPU used during training: 8 Image made courtesy of Taro Amagai Credit would be much appreciated if you used this model Discord: or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely.
Comments

AIDontEvenKnow
This audio sample's pitching was raised by 12 due to using a male vocal track when generating.

AIDontEvenKnow
This audio sample's pitching was increased by 12 due to using a male vocal track when generating for better accuracy.
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