Description
not the best one yet, since there's literally some peaking in the dataset. this character is featured in uma musume: pretty derby! (both anime and game) trained on 17 minutes of audio data (thank you maki ligon for the dataset (yet again)) cv. Chisa Kimura pitch extraction: mangio-crepe (48 hops) steps: 16.5k batch size: 8 huggingface:
Comments

sxndypz
if mixed properly, the peaking won't be noticable

sxndypz
i think
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