RVC-Project/Retrieval-based-Voice-Conversion-WebUI
Vedi su GitHubIs it expected that v2 trained models underperform compared to v1 trained models on identical settings?
Open
#297 aperta il 16 mag 2023
bughelp wantedquestion
Metriche repository
- Star
- (18.427 star)
- Metriche merge PR
- (Nessuna PR mergiata in 30 g)
Descrizione
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?