Added docs

EX3exp · Oct 5, 2024 · 556b66c · 556b66c
1 parent 55a822a
commit 556b66c
Show file tree

Hide file tree

Showing 9 changed files with 446 additions and 2 deletions.
diff --git a/Misc/voicer-yaml.png b/Misc/voicer-yaml.png
diff --git a/README.md b/README.md
@@ -1,2 +1,46 @@
-# MiriVoice
- (still working)Open TTS platform for everyone
+### MiriVoice
+## [<img src="Misc\title.png" height="57"/>](README.md)
+📜🧐 :
+[English](README.md) | [한국어](readme/README-ko.md)
+#### [EN]
+
+`MiriVoice` is **Free**, Open-Source TTS Engine Application for all.
+
+<img src="Misc\app_preview.jpg" height="210"/>
+
+### 📁 Download MiriVoice
+
+[![Getting Started](https://img.shields.io/badge/Download-%23f9fc14?style=for-the-badge&logo=windows&logoSize=auto&labelColor=%230d0d0c)](get-started.md)
+
+### 📁 Make Your Voicer
+[![VITS2 Support](https://img.shields.io/badge/Make_VITS2_Voicer-%231f7a28?style=for-the-badge&logo=windows&logoSize=auto)](model-support-doc\VITS2\make-voicer-VITS2.md)
+
+
+
+### 📚  Features :
+    ❇️ 1. Simple, User-centered UI/UX.   
+    ❇️ 2. Cross-Platform.   
+    ❇️ 3. Versatile design, to support worldwide Languages & TTS Models.  
+
+
+### 🔖 Model Supported List
+✅ **VITS2**  | [Paper](https://arxiv.org/abs/2307.16430)
+
+### 🔖 Language Supported List
+#### 1. UI
+✅ **English**   
+✅ **한국어**   
+#### 2. Phonemizer
+✅ **IPA (default)**   
+✅ **American English (en-US)**   
+✅ **한국어 (ko)**
+
+## ❤️ Support MiriVoice
+- Developing TTS Models sometimes requires money💸... <br> Be MiriVoice's supporter for more free finetuning models, various models support, etc!
+
+    [!["Buy Me A Coffee"](https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png)](https://buymeacoffee.com/inthe6788f
+)
+
+##  🔖 News :
+- 🔈2024.10.06 MiriVoice Released with **VITS2** Support!
+<br>    Thanks to @2xxbin for MacOS Testing & Debugging Support.
diff --git a/get-started.md b/get-started.md
@@ -0,0 +1,43 @@
+### MiriVoice - Get Started
+[<img src="Misc\title.png" height="57"/>](README.md)
+
+📜🧐 :
+[English](get-started.md) | [한국어](readme/get-started-ko.md)
+#### [EN]
+
+- ❇️ `MiriVoice` is **.NET 8** Application. 
+- ❇️ If you're not sure with your OS, check [here (.NET 8 - Supported OS versions)](https://github.com/dotnet/core/blob/main/release-notes/8.0/supported-os.md).
+
+## 1. Windows 64bit (x64)
+- ❇️ 1. Click button to download.
+
+    [![Download](https://img.shields.io/badge/Download-Windows_64bit-blue?style=for-the-badge&logo=windows&logoSize=auto)](https://github.com/EX3exp/MiriVoice/releases/latest/download/MiriVoice-win-x64.zip)
+
+
+- ❇️ 2. Extract `MiriVoice-win-x64.zip`.
+- ❇️ 3. Double click `MiriVoice.exe`.
+
+## 2. Windows 32bit (x84)
+- ❇️ 1. Click button to download.
+
+    [![Download](https://img.shields.io/badge/Download-Windows_32bit-blue?style=for-the-badge&logo=windows&logoSize=auto)](https://github.com/EX3exp/MiriVoice/releases/latest/download/MiriVoice-win-x84.zip) 
+
+
+- ❇️ 2. Extract `MiriVoice-win-x84.zip`.
+- ❇️ 3. Double click `MiriVoice.exe`.
+
+## 3. Mac OS (64bit)
+- Currently, it might crash when double-clicked `MiriVoice.app`, You have to double-click `MiriVoice.app/run.sh` instead. Seems to be a tricky bug. 🐛
+- ❇️ 1. Click button to download.
+
+    [![Download](https://img.shields.io/badge/Download-MacOS_64bit-black?style=for-the-badge&logo=windows&logoSize=auto)](https://github.com/EX3exp/MiriVoice/releases/latest/download/MiriVoice-osx-x64.zip)
+- ❇️ 2. Extract `MiriVoice-osx-x64.zip` in `Application` folder.
+- ❇️ 3. Double click `MiriVoice.app/run.sh`.
+
+## 4. Linux (64bit)
+- Please note that Linux version is not tested, There may be some issues.
+- ❇️ 1. Click button to download.
+
+    [![Download](https://img.shields.io/badge/Download-Linux_64bit-orange?style=for-the-badge&logo=windows&logoSize=auto)](https://github.com/EX3exp/MiriVoice/releases/latest/download/MiriVoice-linux-x64.tar.gz)
+
+- ❇️ 2. Extract `MiriVoice-linux-x64.tar.gz`.
diff --git a/model-support-doc/VITS2/make-voicer-VITS2-ko.md b/model-support-doc/VITS2/make-voicer-VITS2-ko.md
@@ -0,0 +1,100 @@
+### 미리보이스 - 성우 만들기 (VITS2)
+[<img src="..\..\Misc\title.png" height="57"/>](../../readme/README-ko.md)
+
+📜🧐 :
+[English](make-voicer-VITS2.md) | [한국어](make-voicer-VITS2-ko.md)
+#### [KO]
+
+## 📚 1. 개괄
+- `VITS2` 모델을 훈련해 봅시다.
+- [VITS2 모델에 관해 더 알고 싶다면 (VITS2 논문)](https://arxiv.org/abs/2307.16430)
+
+## 📚 2. 준비물
+### ❇️ 1. 녹음본 - `recorded.zip`
+- 먼저 **말뭉치**를 읽어 녹음한 녹음본이 필요해요. 
+> 🤔말뭉치가 뭐에요?
+> - 말뭉치는 **여러 문장들을 모은 것**을 의미해요.
+> - 말뭉치가 쓰이는 분야는 매우 많습니다. 우리는 이 글에서 '말뭉치'를 **TTS 모델 훈련에 사용되는 데이터셋**으로 지칭할 거에요.
+
+
+> 🤔어떤 말뭉치를 사용해야 하죠? 녹음은 어떻게 하나요?
+> - [Recstar](https://github.com/sdercolin/recstar)를 사용해도 좋고, 다른 녹음 프로그램을 사용해도 좋아요.
+> - 말뭉치는 **[MiriVoiceSupport-CorpusManager](https://github.com/EX3exp/MiriVoiceSupport-CorpusManager/blob/main/readme/README-ko.md)에서 다운받을 수 있어요.     
+>   녹음을 끝낸 후, 하단의 지시사항들을 계속 따라가세요!**
+> - *원한다면, 스스로 `dataset.zip`을 만들어 사용해도 됩니다.*
+
+<br>
+
+❇️ 녹음이 끝났다면, 많은 wav 파일들이 보일 거에요.<br>
+각 wav 파일들을 **한 폴더** 안에 모아 주세요. 
+
+예시:
+```
+📂 recorded
+├─ 💿MV-KOR-AA-NORMAL_0-001.wav
+├─ 💿MV-KOR-AA-NORMAL_0-002.wav
+├─ 💿MV-KOR-AA-NORMAL_0-012.wav
+├─ 💿MV-KOR-AA-BRIGHT_1-001.wav
+├─ 💿MV-KOR-AA-BRIGHT_1-022.wav
+└─ ... 
+```
+그리고 `.zip`으로 압축해 주세요.
+```
+🗂️ recorded.zip
+├─ 💿MV-KOR-AA-NORMAL_0-001.wav
+├─ 💿MV-KOR-AA-NORMAL_0-002.wav
+├─ 💿MV-KOR-AA-NORMAL_0-012.wav
+├─ 💿MV-KOR-AA-BRIGHT_1-001.wav
+├─ 💿MV-KOR-AA-BRIGHT_1-022.wav
+└─ ... 
+```
+
+❇️ 멋진 `recorded.zip` 을 얻었어요. **이제 이걸 가지고 `dataset.zip` 을 만들어야 합니다**.
+- 🔽 아래를 누르면, 이 노트북 친구가 `dataset.zip`을 만들어 줄 거에요.
+
+    [<img src="https://colab.research.google.com/assets/colab-badge.svg">](https://colab.research.google.com/github/EX3exp/MiriVoiceSupport-CorpusManager/blob/main/MiriVoice_Corpus_Dataset_Generator.ipynb)
+
+
+### ❇️ 2. 데이터셋  - `dataset.zip`
+- 아마 아래의 구조를 띤 `dataset.zip`이 구글 드라이브에 생성되어 있을 거에요.
+```
+🗂️ dataset.zip
+├─ 📂train
+│  ├─ 📜filelist_train.txt.cleaned
+│  ├─ 💿MV-KOR-AA-NORMAL_0-001.wav
+│  ├─ 💿MV-KOR-AA-NORMAL_0-002.wav
+│  ├─ 💿MV-KOR-AA-BRIGHT_1-001.wav
+│  └─ ... 
+└─ 📂validation
+   ├─ 📜filelist_val.txt.cleaned
+   ├─ 💿MV-KOR-AA-NORMAL_0-012.wav
+   ├─ 💿MV-KOR-AA-BRIGHT_1-022.wav
+   └─ ...
+```
+### ❇️ 3. VITS2 훈련 노트북
+- 🔽 아래를 눌러 훈련 노트북을 실행하세요.
+
+    [<img src="https://colab.research.google.com/assets/colab-badge.svg">](https://colab.research.google.com/github/EX3exp/MiriVoiceSupport-VITS2/blob/main/VITS2_MiriVoice_Support.ipynb)
+
+
+### ❇️ 4. VITS2 Voicer Export Notebook
+- 훈련이 끝났다면, `G_*.pth`, `D_*.pth` 파일이 있을 거에요. 가장 마음에 드는 체크포인트를 골라 줍니다.
+- 우린 `미리보이스`에서 `.pth` 파일을 사용할 수 없어서, `.onnx`로 변환해 주어야 해요.
+- 🔽 아래를 눌러 노트북을 실행하세요. 모델을 `미리보이스`에서 구동되는 성우로 내보낼 거에요.
+
+    [<img src="https://colab.research.google.com/assets/colab-badge.svg">]("https://colab.research.google.com/github/EX3exp/MiriVoiceSupport-VITS2/blob/main/MiriVoicer_VITS2_Exporter.ipynb)
+
+- 아래와 같은 `<성우 이름>.zip`이 생겼을 거에요. :
+    ```
+    🗂️ <성우 이름>.zip
+    ├─ ⬜voicer.onnx
+    ├─ 📜voicer.yaml
+    ├─ 📜config.yaml
+    └─ 📜readme.txt
+    ```    
+- `voicer.yaml`을 편집해 아이콘이나 전신 일러스트 등을 바꾸거나, 추가할 수 있어요. [이곳](../../readme/voicer-yaml-ko.md)을 읽어 보세요.
+
+### ❇️ 5. 미리보이스에 성우 설치하기
+1. `도구` -> `성우 설치`를 클릭하세요.
+2. `<성우 이름>.zip`을 열고 기다립니다. `<성우 이름>.zip`이 `Voicer` 폴더 내에 압축 해제될 거에요.
+3. 완료! 이제 성우를 사용할 수 있어요.
diff --git a/model-support-doc/VITS2/make-voicer-VITS2.md b/model-support-doc/VITS2/make-voicer-VITS2.md
@@ -0,0 +1,98 @@
+### MiriVoice - Make Voicer (VITS2)
+[<img src="..\..\Misc\title.png" height="57"/>](../../README.md)
+
+📜🧐 :
+[English](make-voicer-VITS2.md) | [한국어](make-voicer-VITS2-ko.md)
+#### [EN]
+
+## 📚 1. Abstract
+- We will train `VITS2` model in this page.
+- [More About VITS2 Model (VITS2 Paper)](https://arxiv.org/abs/2307.16430)
+
+## 📚 2. Things to Prepare
+### ❇️ 1. Recorded Samples - `recorded.zip`
+- First, you have to record samples, by reading **Corpus** line by line.
+> 🤔What is Corpus?
+> - Corpus means **a collection of texts**. (And its plural form is 'Corpora'.)
+> - The Fields that Corpora are used is enormous, but in our case, We will treat the word 'Corpus' as **Dataset for TTS Model's train**.
+
+
+> 🤔What Corpus should I use? How Can I record them?
+> - You can use [Recstar](https://github.com/sdercolin/recstar), or other Recording Software.
+> - **You can just download one from [MiriVoiceSupport-CorpusManager](https://github.com/EX3exp/MiriVoiceSupport-CorpusManager/blob/main/README.md).
+>   After finishing your recording, please follow instructions below!**
+> - *If you want, you can make your own `dataset.zip` yourself.*
+
+<br>
+
+❇️ After Recording, We will have bunch of wav files.<br>
+Please collect each wav files into **One Folder**, like below:
+```
+📂 recorded
+├─ 💿MV-KOR-AA-NORMAL_0-001.wav
+├─ 💿MV-KOR-AA-NORMAL_0-002.wav
+├─ 💿MV-KOR-AA-NORMAL_0-012.wav
+├─ 💿MV-KOR-AA-BRIGHT_1-001.wav
+├─ 💿MV-KOR-AA-BRIGHT_1-022.wav
+└─ ... 
+```
+Then compress into `.zip`.
+```
+🗂️ recorded.zip
+├─ 💿MV-KOR-AA-NORMAL_0-001.wav
+├─ 💿MV-KOR-AA-NORMAL_0-002.wav
+├─ 💿MV-KOR-AA-NORMAL_0-012.wav
+├─ 💿MV-KOR-AA-BRIGHT_1-001.wav
+├─ 💿MV-KOR-AA-BRIGHT_1-022.wav
+└─ ... 
+```
+
+❇️ We're having nice `recorded.zip` now, **all we have to do is making `dataset.zip` with it.**
+- 🔽 Please click below, this notebook will do every `dataset.zip` stuffs for you!
+
+    [<img src="https://colab.research.google.com/assets/colab-badge.svg">](https://colab.research.google.com/github/EX3exp/MiriVoiceSupport-CorpusManager/blob/main/MiriVoice_Corpus_Dataset_Generator.ipynb)
+
+
+### ❇️ 2. Dataset - `dataset.zip`
+- You will having `dataset.zip` with below structure, it might be already generated in proper google drive's path.
+```
+🗂️ dataset.zip
+├─ 📂train
+│  ├─ 📜filelist_train.txt.cleaned
+│  ├─ 💿MV-KOR-AA-NORMAL_0-001.wav
+│  ├─ 💿MV-KOR-AA-NORMAL_0-002.wav
+│  ├─ 💿MV-KOR-AA-BRIGHT_1-001.wav
+│  └─ ... 
+└─ 📂validation
+   ├─ 📜filelist_val.txt.cleaned
+   ├─ 💿MV-KOR-AA-NORMAL_0-012.wav
+   ├─ 💿MV-KOR-AA-BRIGHT_1-022.wav
+   └─ ...
+```
+### ❇️ 3. VITS2 Training Notebook
+- 🔽 Click below and run the Colab Notebook.
+
+    [<img src="https://colab.research.google.com/assets/colab-badge.svg">](https://colab.research.google.com/github/EX3exp/MiriVoiceSupport-VITS2/blob/main/VITS2_MiriVoice_Support.ipynb)
+
+
+### ❇️ 4. VITS2 Voicer Export Notebook
+- After training, we will having `G_*.pth`, `D_*.pth`. Please choose one best checkpoint.
+- We cannot use `.pth` file in `MiriVoice`. We need to convert it into `.onnx` format.
+- 🔽 Click below to export your model into `MiriVoice`'s Voicer format.
+
+    [<img src="https://colab.research.google.com/assets/colab-badge.svg">]("https://colab.research.google.com/github/EX3exp/MiriVoiceSupport-VITS2/blob/main/MiriVoicer_VITS2_Exporter.ipynb)
+
+- You will now have `<voicer name>.zip` now, like :
+    ```
+    🗂️ <voicer name>.zip
+    ├─ ⬜voicer.onnx
+    ├─ 📜voicer.yaml
+    ├─ 📜config.yaml
+    └─ 📜readme.txt
+    ```    
+- You can edit `voicer.yaml` to add icon or protrait, [please see here.](../../voicer-yaml.md)
+
+### ❇️ 5. Install Voicer in MiriVoice
+1. Click `Tools` -> `Install Voicer`.
+2. Open your `<voicer name>.zip` and wait. Your `<voicer name>.zip` will be extracted in `Voicer` Folder.
+3. Done! You can use your voicer now.
diff --git a/readme/README-ko.md b/readme/README-ko.md
@@ -0,0 +1,42 @@
+### 미리보이스
+## [<img src="..\Misc\title.png" height="57"/>](README-ko.md)
+📜🧐 :
+[English](../README.md) | [한국어](README-ko.md)
+#### [KO]
+
+`미리보이스`는 모두를 위한 **무료** 오픈소스 TTS 엔진이에요.
+
+<img src="..\Misc\app_preview.jpg" height="210"/>
+
+### 📁 미리보이스 다운로드
+
+[![Getting Started](https://img.shields.io/badge/다운로드-%23f9fc14?style=for-the-badge&logo=windows&logoSize=auto&labelColor=%230d0d0c)](get-started-ko.md)
+
+### 📁 성우 만들기
+[![VITS2 Support](https://img.shields.io/badge/VITS2_성우_만들기-%231f7a28?style=for-the-badge&logo=windows&logoSize=auto)](..\model-support-doc\VITS2\make-voicer-VITS2-ko.md)
+
+
+
+### 📚  특성 :
+    ❇️ 1. 간단하고 이용자 친화적인 UI/UX.   
+    ❇️ 2. 크로스 플랫폼 지원.   
+    ❇️ 3. 전 세계의 언어와 모델을 담기 위한 다용도적 설계.  
+
+
+### 🔖 지원되는 모델들
+✅ **VITS2**  | [논문](https://arxiv.org/abs/2307.16430)
+
+### 🔖 지원되는 언어들
+#### 1. UI
+✅ **English**   
+✅ **한국어**
+#### 2. 음소화기
+✅ **IPA (default)**   
+✅ **American English (en-US)**   
+✅ **한국어 (ko)**
+
+## ❤️ 미리보이스 후원하기
+- TTS 모델 제작엔 때로 돈이 많이 들어가곤 해요💸... <br> 더 많은 무료 파인튜닝 모델 제작, 더 많은 모델 지원을 위해 미리보이스를 후원해 주세요!
+
+    [!["Buy Me A Coffee"](https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png)](https://buymeacoffee.com/inthe6788f
+)
diff --git a/readme/get-started-ko.md b/readme/get-started-ko.md
@@ -0,0 +1,43 @@
+### 미리보이스 - 시작 가이드
+[<img src="..\Misc\title.png" height="57"/>](README-ko.md)
+
+📜🧐 :
+[English](..\get-started.md) | [한국어](get-started-ko.md)
+#### [KO]
+
+- ❇️ `미리보이스` 는 **.NET 8** 어플리케이션이에요.
+- ❇️ 자신의 운영체제가 **.NET 8**을 지원하는지 확신이 안 선다면, [이곳 (.NET 8 - Supported OS versions)](https://github.com/dotnet/core/blob/main/release-notes/8.0/supported-os.md)을 읽어 보세요.
+
+## 1. Windows(윈도우) 64bit (x64)
+- ❇️ 1. 버튼을 눌러 다운로드합니다.
+
+    [![Download](https://img.shields.io/badge/다운로드-Windows_64bit-blue?style=for-the-badge&logo=windows&logoSize=auto)](https://github.com/EX3exp/MiriVoice/releases/latest/download/MiriVoice-win-x64.zip)
+
+
+- ❇️ 2. `MiriVoice-win-x64.zip`을 압축 해제합니다.
+- ❇️ 3. `MiriVoice.exe`를 더블 클릭하세요.
+
+## 2. Windows(윈도우) 32bit (x84)
+- ❇️ 1. 버튼을 눌러 다운로드합니다.
+
+    [![Download](https://img.shields.io/badge/다운로드-Windows_32bit-blue?style=for-the-badge&logo=windows&logoSize=auto)](https://github.com/EX3exp/MiriVoice/releases/latest/download/MiriVoice-win-x84.zip) 
+
+
+- ❇️ 2. `MiriVoice-win-x84.zip`을 압축 해제합니다.
+- ❇️ 3. `MiriVoice.exe`를 더블 클릭하세요.
+
+## 3. Mac OS(맥) (64bit)
+- 현재 원인불명의 버그🐛가 있어, `MiriVoice.app`을 더블 클릭하면 프로그램이 즉시 종료될 수 있어요. 반드시 `MiriVoice.app/run.sh`를 눌러 실행해 주세요. 
+- ❇️ 1. 버튼을 눌러 다운로드합니다.
+
+    [![Download](https://img.shields.io/badge/다운로드-MacOS_64bit-black?style=for-the-badge&logo=windows&logoSize=auto)](https://github.com/EX3exp/MiriVoice/releases/latest/download/MiriVoice-osx-x64.zip)
+- ❇️ 2. `MiriVoice-osx-x64.zip`를 `Application` 폴더에 압축 해제합니다.
+- ❇️ 3. `MiriVoice.app/run.sh`를 더블 클릭하세요.
+
+## 4. Linux(리눅스) (64bit)
+- 현재 리눅스에서는 제대로 테스트가 이루어지지 않았어요. 프로그램에 문제가 있을 수 있으니, 이 점 양해해 주세요.
+- ❇️ 1. 버튼을 눌러 다운로드합니다.
+
+    [![Download](https://img.shields.io/badge/다운로드-Linux_64bit-orange?style=for-the-badge&logo=windows&logoSize=auto)](https://github.com/EX3exp/MiriVoice/releases/latest/download/MiriVoice-linux-x64.tar.gz)
+
+- ❇️ 2. `MiriVoice-linux-x64.tar.gz`를 압축 해제합니다.