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 geöffnet am 16. Mai 2023

Auf GitHub ansehen
 (6 Kommentare) (0 Reaktionen) (0 zugewiesene Personen)Python (2.849 Forks)batch import
bughelp wantedquestion

Repository-Metriken

Stars
 (18.427 Stars)
PR-Merge-Metriken
 (Keine gemergten PRs in 30 T)

Beschreibung

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?

Contributor Guide