Skip to content

Commit

Permalink
edit readme
Browse files Browse the repository at this point in the history
  • Loading branch information
kdrkdrkdr committed Jun 28, 2023
1 parent 7243ebc commit 6a036df
Showing 1 changed file with 2 additions and 11 deletions.
13 changes: 2 additions & 11 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,16 +4,6 @@ This Repository can speak Japanese even if you train with Korean dataset, and ca
By transcribing pronunciation from Japanese to Korean and Korean to Japanese, the unstable voice produced when using the existing multilingual ipa cleaners has been improved.



## Table of Contents
- [Prerequisites](#prerequisites)
- [Installation](#installation)
- [Prepare_Datasets](#Prepare_Datasets)
- [Usage](#usage)
- [Inference](#inference)
- [References](#References)


## Pre-requisites
- A Windows/Linux system with a minimum of `16GB` RAM.
- A GPU with at least `12GB` of VRAM.
Expand Down Expand Up @@ -82,8 +72,9 @@ python preprocess.py --filelists filelists/train.txt filelists/val.txt
* If you train with korean dataset, refer [configs/ko.json](configs/ko.json)

- You can download and use [pretrained_model](https://github.com/kdrkdrkdr/JK-VITS/releases) to finetuning.
* If you train with korean dataset, use [korean_pretrained_dataset](https://github.com/kdrkdrkdr/JK-VITS/releases/tag/korean_pretrained_model) (Completed)
* If you train with japanese dataset, use [japanese_pretrained_dataset](https://github.com/kdrkdrkdr/JK-VITS/releases/tag/japanese_pretrained_model) (Work In Process)
* If you train with korean dataset, use [korean_pretrained_dataset](https://github.com/kdrkdrkdr/JK-VITS/releases/tag/korean_pretrained_model) (Completed)


- Write Transcripts.
* If you train with japanese dataset
Expand Down

0 comments on commit 6a036df

Please sign in to comment.