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

Training issue with DirectML

Open
#1,067 15 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hello!

I just downloaded RVC0813AMD_Intel.7z from HuggingFace, great work on the release by the way!

I have an AMD RX 6750 XT 12 GB GPU and when training everything works and it uses my AMD GPU as in Task Manager it shows my GPU usage going to ~80% when extracting pitch with rmvpe_gpu, but when I get to the button "Train Model" and hit it the CMD window say's "NO GPU DETECTED: falling back to CPU - this may take a while". For the GPU Index I put "0" without quotes, I've also put "0-1-2" without quotes, but it still say's the same error.

Any tips/help? Thanks!

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 at the “Train Model” entry point in the downloaded RVC0813AMD_Intel release and compare its GPU detection with the working rmvpe_gpu extraction path. Reproduce the “NO GPU DETECTED” fallback with GPU Index 0, then document a confirmed DirectML/AMD setup or the limitation; no source file or test is named in the issue.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.