Description
the models needs to be pitched down from -4 to -24 depending on the used audio / pretty weird this wasn't done before / dataset was 7 minutes
Comments
PlasmaTi
the models needs to be pitched down from -4 to -24 depending on the used audio / pretty weird this was done before / dataset was 7 minutes https://huggingface.co/Plasmati/AIDRIVEORNOTMODELS6/resolve/main/Tommy-Shelby.zip?download=true
PlasmaTi
Talking Sample -
PlasmaTi
Talking Curve Singing Sample - https://sndup.net/yzt7/
PlasmaTi
FTA Singing Sample - https://sndup.net/sh4v/
PlasmaTi
Model works much better with talking
PlasmaTi
just tried singing to see how it sounded
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