RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Is it expected that v2 trained models underperform compared to v1 trained models on identical settings?

開放

#297 建立於 2023年5月16日

 (6 則留言) (0 個反應) (0 位負責人)Python (2,849 個分叉)batch import
bughelp wantedquestion

倉庫指標

星標
 (18,427 顆星)
PR 合併指標
 (30 天內沒有已合併 PR)

描述

v1_vs_v2_Examples.zip

5 minute dataset. I also used the Mangio fork which adds 'crepe' as a training option for both of these models. Maybe for a model with a bigger dataset like 40 minutes, v2 outperforms?

貢獻者指南