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 opened on May 16, 2023

View on GitHub
 (6 comments) (0 reactions) (0 assignees)Python (2,849 forks)batch import
bughelp wantedquestion

Repository metrics

Stars
 (18,427 stars)
PR merge metrics
 (No merged PRs in 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?

Contributor guide

Research direction
Compare the training scripts and model architectures between v1 and v2. Train both versions on a larger dataset (e.g., 40 minutes) and evaluate performance metrics like similarity and naturalness. Also check if the Crepe option in the Mangio fork affects results differently.
Tech stack
pythonpytorch
Domain
aimachine learning
Issue type
Research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorchaudio processing basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60