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

Can I create a small final Model from "model and optimizer state" (epoch-) saves?

Open
#2,352 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
38.4k
Forks
5.3k
PR merge metrics
No merged PRs in 30d

Description

Hi,
yesterday I trained a new Model with 1000 Epochs, but I forgot to check the "Save a small final model to the 'weights' folder at each save point" option. While training I let RVC save every 5th epoch the model and optimizer state. Tensorboard now shows me, that step 15.800 out of 19.800 could be the best. Is there a possibility to create a small final model from those big G_15800.pth and D_15800.pth files later (now) without needing to do the whole training again? ? Please, help :D

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating the handling for the “Save a small final model” option and the model and optimizer state files named G_15800.pth and D_15800.pth. Determine whether those files can produce the requested small final model without retraining; done means the conversion path is available or the limitation is clearly documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.