Origin: HoloMyth (Hololive English) Dataset: 59 minutes and 59 seconds of Mori talking Batch size per GPU used during training: 4 Sample rate: 32k Image made courtesy of Kurohoshi (@96hoshii_0317) Credit would be much appreciated if you used this model -- Discord: @RigidSpinner or YouTube: @AIDontEvenKnow-cd8qe You are solely responsible with what you create with this model so use wisely. https://huggingface.co/Gigrig/GigrigRVC/resolve/main/CalliopeMori_RVC_v2_Itaila_e200_s89000.zip?download=true

rigid have you tried the titan pretrain?

No, I had not. I was thinking of doing a comparison with the Itaila and Titan pretrains to see how they sound. I'll probably think about it once Titan Large is available.