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

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

Open

#297 建立於 2023年5月16日

在 GitHub 查看
 (6 留言) (0 反應) (0 負責人)Python (2,849 fork)batch import
bughelp wantedquestion

倉庫指標

Star
 (18,427 star)
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