RVC-Project/Retrieval-based-Voice-Conversion-WebUI
GitHub で見るIs it expected that v2 trained models underperform compared to v1 trained models on identical settings?
Open
#297 opened on 2023年5月16日
bughelp wantedquestion
Repository metrics
- Stars
- (18,427 stars)
- PR merge metrics
- (30d に merged PR はありません)
説明
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?