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 aberto em 16 de mai. de 2023

Ver no GitHub
 (6 comments) (0 reactions) (0 assignees)Python (2.849 forks)batch import
bughelp wantedquestion

Métricas do repositório

Stars
 (18.427 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

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?

Guia do colaborador