RVC-Project/Retrieval-based-Voice-Conversion-WebUI

Very long epoch generation

Open

#840 opened on Jul 23, 2023

View on GitHub
 (18 comments) (0 reactions) (0 assignees)Python (2,849 forks)batch import
bugenhancementfollowing uphelp wantedquestiontodo list

Repository metrics

Stars
 (18,427 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

I have 1277 around 5s wav files for training. On my RTX 3080 it took 13 hours to generate 10 epochs, using 26 batch size. Is it normal for it to take so long with this dataset? I want to train on total 200 epochs, how do I go about it then?

Contributor guide

Research direction
Investigate the relationship between training time and dataset size. Check if the model architecture or hyperparameters (batch size, learning rate) can be optimized. Consider using mixed precision training or gradient accumulation. Explore if the dataset can be reduced or augmented more efficiently.
Tech stack
python
Domain
machine learning
Issue type
Performance
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.
Needs investigation
Prerequisites
PythonMachine Learning basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50