Description
with 2 minutes and 15 seconds of dataset from the movie (I only pick the parts where his voice is clear and no SFX and other voices are interfering, that's why he's lacking dataset) Normalized + Vocals Isolated using UVR Voiced by Zach Aguilar 4.8k Steps RVMPE/64 Hop-Length 48k Target Sample Batch Size 7
Comments

🔗Link: https://huggingface.co/SyberGen/DragonBallVModels/resolve/main/DrHedo.zip?download=true > 🚆Trained with 2 minutes and 15 seconds of dataset from the movie (I only pick the parts where his voice is clear and no SFX and other voices are interfering, that's why he's lacking dataset) > ✨Normalized + Vocals Isolated using UVR > 🎙️Voiced by Zach Aguilar > > 👟 4.8k Steps > 🔊 RVMPE/64 Hop-Length > 🎯 48k Target Sample > 💼 Batch Size 7
Add a comment
Samples
Pitch