awawawawawawawawawaawawawawaaw 2.0: the grand return

sounds clearer than the jelly model i've made earlier

trained on 17 minutes of data from her malware stream
(xminus mel roformer + uvr de-reverb (the new x-minus one, not the de-echo-de-reverb one), rx11 de-plosive + de-click)

pitch extraction: rmvpe
steps: 15.5k
batch size: 7
pretrain: klm 4.1 / 32k

huggingface: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/jelly_act2.zip

Additional Details:

Tags: No tags available

Download Link: https://huggingface.co/sxndypz/rvc-v2-models/resolve/main/jelly_act2.zip