From 1a873a6f838e43314a79de5cffaf951fb2b81e33 Mon Sep 17 00:00:00 2001 From: Plachta Date: Sun, 26 Feb 2023 20:23:53 +0800 Subject: [PATCH] updated pipeline --- README_EN.md | 75 ---------------------------------------------------- README_ZH.md | 2 +- 2 files changed, 1 insertion(+), 76 deletions(-) delete mode 100644 README_EN.md diff --git a/README_EN.md b/README_EN.md deleted file mode 100644 index 69d75d0..0000000 --- a/README_EN.md +++ /dev/null @@ -1,75 +0,0 @@ -[中文文档请点击这里](https://github.com/Plachtaa/VITS-fast-fine-tuning/blob/main/README_ZH.md) -# VITS Fast Fine-tuning -This repo will guide you to add your own character voices, or even your own voice, into an existing VITS TTS model -to make it able to do the following tasks in less than 1 hour: - -1. Any-to-any voice conversion between you & any characters you added & preset characters -2. English, Japanese & Chinese Text-to-Speech synthesis with the characters you added & preset characters - -Welcome to play around with the base model, a Trilingual Anime VITS! -[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer) - -### Currently Supported Tasks: -- [x] Convert user's voice to characters listed [here](https://github.com/SongtingLiu/VITS_voice_conversion/blob/main/configs/finetune_speaker.json) -- [x] Chinese, English, Japanese TTS with user's voice -- [x] Chinese, English, Japanese TTS with custom characters! - -### Currently Supported Characters for TTS & VC: -- [x] Umamusume Pretty Derby (Used as base model pretraining) -- [x] Sanoba Witch (Used as base model pretraining) -- [x] Genshin Impact (Used as base model pretraining) -- [x] Any character you wish as long as you have their voices! - - - - -## Fine-tuning -It's recommended to perform fine-tuning on [Google Colab](https://colab.research.google.com/drive/1omMhfYKrAAQ7a6zOCsyqpla-wU-QyfZn?usp=sharing) -because the original VITS has some dependencies that are difficult to configure. - -### How long does it take? -1. Install dependencies (2 min) -2. Record at least 20 your own voice, the content to read will be presented in UI, less than 20 words per sentence. (5~10 min) -3. Upload your character voices, which should be a `.zip` file, -it's file structure should be like: -``` -Your-zip-file.zip -├───Character_name_1 -├ ├───xxx.wav -├ ├───... -├ ├───yyy.mp3 -├ └───zzz.wav -├───Character_name_2 -├ ├───xxx.wav -├ ├───... -├ ├───yyy.mp3 -├ └───zzz.wav -├───... -├ -└───Character_name_n - ├───xxx.wav - ├───... - ├───yyy.mp3 - └───zzz.wav -``` -Note that the format & name of the audio files does not matter as long as they are audio files. -Audio quality requirements: >=2s, <=20s per audio, background noise should be as less as possible. -Audio quantity requirements: at least 10 per character, better if 20+ per character. -You can either choose to perform step 2, 3, or both, depending on your needs. - -4. Fine-tune (30 min) -After everything is done, download the fine-tuned model & model config - -## Inference or Usage (Currently support Windows only) -0. Remember to download your fine-tuned model! -1. Download the latest release -2. Put your model & config file into the folder `inference`, make sure to rename the model to `G_latest.pth` and config file to `finetune_speaker.json` -3. The file structure should be as follows: -```shell -inference -├───inference.exe -├───... -├───finetune_speaker.json -└───G_latest.pth -``` -4. run `inference.exe`, the browser should pop up automatically. diff --git a/README_ZH.md b/README_ZH.md index 09eb8b5..fdc4f87 100644 --- a/README_ZH.md +++ b/README_ZH.md @@ -1,4 +1,4 @@ -English Documentation Please Click [here](https://github.com/Plachtaa/VITS-fast-fine-tuning/blob/main/README_EN.md) +English Documentation Please Click [here](https://github.com/Plachtaa/VITS-fast-fine-tuning/blob/main/README.md) # VITS 快速微调 这个代码库会指导你如何将自定义角色（甚至你自己），加入预训练的VITS模型中，在1小时内的微调使模型具备如下功能： 1. 在 模型所包含的任意两个角色 之间进行声线转换