Dizzy Dokuro (ACT2) (Phase Connect) (RVC v2) - 380 Epochs | AI HUB | Page 1

outer frigate Dec 15, 2024, 12:19 PM

#

new month. new voice model.
this voice model may sound a bit worse than the old dizzy model i made earlier

trained on 16 minutes of audio data from her recent streams. (unwa's mel roformer + uvr de-reverb + rx de-click + de-plosive + eq)

pitch extraction: rmvpe
steps: 18.9k / 19k steps
batch size: 7
pretrain: klm 4.1 / 32k

#

if you like the old voice model of her better: #1205791695107657748

frank jungleBOT Dec 15, 2024, 12:49 PM

#

Model Ready ✅

This model has been synced with Weights and is ready to use for free!

frank jungleBOT Dec 15, 2024, 12:49 PM

#

outer frigate Dec 22, 2024, 1:49 AM

#

i think i'm falling off in terms of making voice models

outer frigate Jan 14, 2025, 10:01 AM

#

next model's going to be howan from show by rock!! mashumairesh!!

#

the model after that's going to be delmin

#

also from show by rock!! mashumairesh!!

#Dizzy Dokuro (ACT2) (Phase Connect) (RVC v2) - 380 Epochs