Description

*"Nothing to see here... if u know what i mean"* Dataset processed & model trained by me. Please credit me if you gonna use it publicly Recommended pitch offset: lower-pitch voice: 20+ higher-pitch voice: 3-4 (For reference only, exact value may vary) Trained with 10 minutes of voice in total, including 3:30 clean, untouched voicelines from anime Blu-ray and drama CD, 2:30 selected acapella and 4 minutes straight-up "Akarin" in various tones.