Skip to content

w-okada/rvc-trainer-docker

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RVC Trainer Docker

prerequisite

  • npm: to build docker
  • hugging face account: download pretrained model
  • docker: to run web-ui

Usage

  1. Download pretrained all models from here and copy them to docker_trainer/pretrained.

  2. Download pretrained_v2 all models from here and copy them to docker_trainer/pretrained_v2.

  3. Download hubert_base.pt from here. Copy it to docker_trainer/hubert.

  4. Run npm run build:docker:trainer

  5. Put training data into trainer/raw-data

  6. Launch docker image bash start_trainer.sh

  7. In docker container, run cp -r logs_org/mute logs/

  8. In docker container, run python infer-web.py

  9. Access the web-ui by the browser. Open tab for training.

    • http://<address>:7865/
  10. Enter the speaker's name. Foler name includes the training data is /rvc/raw-data.

  11. Run the training as usual.

  12. The weights is in trainer/weights. .index is in trainer/logs//

  13. Run with VC_Client!

RVC v2

Select v2 like as the below image.

image

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published