model info:
dataset: 10:58 minutes, audio extracted from youtube
pitch extraction: mangio-crepe
hop length: 32
steps: 5610
batch size: 4
pretrain and sample rate: klm 4.1, 32k
precision: fp16, graph sync included
note:
please don't forget to credit me when you use this model, and don't reupload any of my models without my permission. otherwise i'll report the stolen model to be taken down.