blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-09-05 15:19:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update Docs

Browse Source 
1. Add Missing VC17
2. Modufied the Order of FFmpeg Installation and Requirements Installation
3. Remove Duplicate FFmpeg
This commit is contained in:
XXXXRT666 2025-05-06 17:03:36 +01:00
parent 04aaa6ae34
commit dfea2563c0
5 changed files with 93 additions and 79 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
README.md
View File

@ -63,31 +63,41 @@ If you are a Windows user (tested with win>=10), you can [download the integrate
### Linux ### Linux
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <CU124|CU128|ROCM|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### macOS ### macOS
**Note: The models trained with GPUs on Macs result in significantly lower quality compared to those trained on other devices, so we are temporarily using CPUs instead.** **Note: The models trained with GPUs on Macs result in significantly lower quality compared to those trained on other devices, so we are temporarily using CPUs instead.**
1. Install Xcode command-line tools by running `xcode-select --install`. Install the program by running the following commands:
2. Install the program by running the following commands:
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### Install Manually ### Install Manually
#### Install Dependences
```bash
conda create -n GPTSoVits python=3.10
conda activate GPTSoVits
pip install -r extra-req.txt --no-deps
pip install -r requirements.txt
```
#### Install FFmpeg #### Install FFmpeg
##### Conda Users ##### Conda Users
```bash ```bash
conda activate GPTSoVits
conda install ffmpeg conda install ffmpeg
``` ```
@ -96,14 +106,13 @@ conda install ffmpeg
```bash ```bash
sudo apt install ffmpeg sudo apt install ffmpeg
sudo apt install libsox-dev sudo apt install libsox-dev
conda install -c conda-forge 'ffmpeg<7'
``` ```
##### Windows Users ##### Windows Users
Download and place [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) and [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) in the GPT-SoVITS root. Download and place [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) and [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) in the GPT-SoVITS root
Install [Visual Studio 2017](https://aka.ms/vs/17/release/vc_redist.x86.exe) (Korean TTS Only) Install [Visual Studio 2017](https://aka.ms/vs/17/release/vc_redist.x86.exe)
##### MacOS Users ##### MacOS Users
@ -111,13 +120,6 @@ Install [Visual Studio 2017](https://aka.ms/vs/17/release/vc_redist.x86.exe) (Ko
brew install ffmpeg brew install ffmpeg
``` ```
#### Install Dependences
```bash
pip install -r extra-req.txt --no-deps
pip install -r requirements.txt
```
### Running GPT-SoVITS with Docker ### Running GPT-SoVITS with Docker
#### Docker Image Selection #### Docker Image Selection

34
docs/cn/README.md
View File

@ -63,31 +63,41 @@
### Linux ### Linux
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <CU124|CU128|ROCM|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### macOS ### macOS
**注: 在 Mac 上使用 GPU 训练的模型效果显著低于其他设备训练的模型, 所以我们暂时使用 CPU 进行训练.** **注: 在 Mac 上使用 GPU 训练的模型效果显著低于其他设备训练的模型, 所以我们暂时使用 CPU 进行训练.**
1. 运行 `xcode-select --install` 安装 Xcode command-line tools. 运行以下的命令来安装本项目:
2. 运行以下的命令来安装本项目:
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### 手动安装 ### 手动安装
#### 安装依赖
```bash
conda create -n GPTSoVits python=3.10
conda activate GPTSoVits
pip install -r extra-req.txt --no-deps
pip install -r requirements.txt
```
#### 安装 FFmpeg #### 安装 FFmpeg
##### Conda 用户 ##### Conda 用户
```bash ```bash
conda activate GPTSoVits
conda install ffmpeg conda install ffmpeg
``` ```
@ -96,14 +106,13 @@ conda install ffmpeg
```bash ```bash
sudo apt install ffmpeg sudo apt install ffmpeg
sudo apt install libsox-dev sudo apt install libsox-dev
conda install -c conda-forge 'ffmpeg<7'
``` ```
##### Windows 用户 ##### Windows 用户
下载并将 [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) 和 [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) 放置在 GPT-SoVITS 根目录下. 下载并将 [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) 和 [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) 放置在 GPT-SoVITS 根目录下
安装 [Visual Studio 2017](https://aka.ms/vs/17/release/vc_redist.x86.exe) 环境(仅限韩语 TTS) 安装 [Visual Studio 2017](https://aka.ms/vs/17/release/vc_redist.x86.exe) 环境
##### MacOS 用户 ##### MacOS 用户
@ -111,13 +120,6 @@ conda install -c conda-forge 'ffmpeg<7'
brew install ffmpeg brew install ffmpeg
``` ```
#### 安装依赖
```bash
pip install -r extra-req.txt --no-deps
pip install -r requirements.txt
```
### 运行 GPT-SoVITS (使用 Docker) ### 运行 GPT-SoVITS (使用 Docker)
#### Docker 镜像选择 #### Docker 镜像选择

36
docs/ja/README.md
View File

@ -57,31 +57,41 @@ Windows ユーザー: (Windows 10 以降でテスト済み)、[統合パッケ
### Linux ### Linux
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <CU124|CU128|ROCM|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### macOS ### macOS
**注: Mac で GPU を使用して訓練されたモデルは、他のデバイスで訓練されたモデルと比較して著しく品質が低下するため、当面は CPU を使用して訓練することを強く推奨します.** **注: Mac で GPU を使用して訓練されたモデルは、他のデバイスで訓練されたモデルと比較して著しく品質が低下するため、当面は CPU を使用して訓練することを強く推奨します.**
1. `xcode-select --install` を実行して、Xcode コマンドラインツールをインストールします. 以下のコマンドを実行してこのプロジェクトをインストールします:
2. 以下のコマンドを実行してこのプロジェクトをインストールします.
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### 手動インストール ### 手動インストール
#### FFmpeg をインストールします. #### 依存関係をインストールします
```bash
conda create -n GPTSoVits python=3.10
conda activate GPTSoVits
pip install -r extra-req.txt --no-deps
pip install -r requirements.txt
```
#### FFmpeg をインストールします
##### Conda ユーザー ##### Conda ユーザー
```bash ```bash
conda activate GPTSoVits
conda install ffmpeg conda install ffmpeg
``` ```
@ -90,12 +100,13 @@ conda install ffmpeg
```bash ```bash
sudo apt install ffmpeg sudo apt install ffmpeg
sudo apt install libsox-dev sudo apt install libsox-dev
conda install -c conda-forge 'ffmpeg<7'
``` ```
##### Windows ユーザー ##### Windows ユーザー
[ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) と [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) をダウンロードし、GPT-SoVITS のルートフォルダに置きます. [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) と [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) をダウンロードし、GPT-SoVITS のルートフォルダに置きます
[Visual Studio 2017](https://aka.ms/vs/17/release/vc_redist.x86.exe) 環境をインストールしてください
##### MacOS ユーザー ##### MacOS ユーザー
@ -103,13 +114,6 @@ conda install -c conda-forge 'ffmpeg<7'
brew install ffmpeg brew install ffmpeg
``` ```
#### 依存関係をインストールします
```bash
pip install -r extra-req.txt --no-deps
pip install -r requirementx.txt
```
### GPT-SoVITS の実行 (Docker 使用) ### GPT-SoVITS の実行 (Docker 使用)
#### Docker イメージの選択 #### Docker イメージの選択

34
docs/ko/README.md
View File

@ -57,31 +57,41 @@ Windows 사용자라면 (win>=10에서 테스트됨), [통합 패키지를 다
### Linux ### Linux
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <CU124|CU128|ROCM|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### macOS ### macOS
**주의: Mac에서 GPU로 훈련된 모델은 다른 OS에서 훈련된 모델에 비해 품질이 낮습니다. 해당 문제를 해결하기 전까지 MacOS에선 CPU를 사용하여 훈련을 진행합니다.** **주의: Mac에서 GPU로 훈련된 모델은 다른 OS에서 훈련된 모델에 비해 품질이 낮습니다. 해당 문제를 해결하기 전까지 MacOS에선 CPU를 사용하여 훈련을 진행합니다.**
1. `xcode-select --install`을 실행하여 Xcode 커맨드라인 도구를 설치하세요. 다음 명령어를 실행하여 이 프로젝트를 설치하세요
2. 다음 명령어를 실행하여 이 프로젝트를 설치하세요.
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### 수동 설치 ### 수동 설치
#### 의존성 설치
```bash
conda create -n GPTSoVits python=3.10
conda activate GPTSoVits
pip install -r extra-req.txt --no-deps
pip install -r requirements.txt
```
#### FFmpeg 설치 #### FFmpeg 설치
##### Conda 사용자 ##### Conda 사용자
```bash ```bash
conda activate GPTSoVits
conda install ffmpeg conda install ffmpeg
``` ```
@ -90,14 +100,13 @@ conda install ffmpeg
```bash ```bash
sudo apt install ffmpeg sudo apt install ffmpeg
sudo apt install libsox-dev sudo apt install libsox-dev
conda install -c conda-forge 'ffmpeg<7'
``` ```
##### Windows 사용자 ##### Windows 사용자
[ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe)와 [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe)를 GPT-SoVITS root 디렉토리에 넣습니다. [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe)와 [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe)를 GPT-SoVITS root 디렉토리에 넣습니다
[Visual Studio 2017](https://aka.ms/vs/17/release/vc_redist.x86.exe) 설치 (Korean TTS 전용) [Visual Studio 2017](https://aka.ms/vs/17/release/vc_redist.x86.exe) 설치
##### MacOS 사용자 ##### MacOS 사용자
@ -105,13 +114,6 @@ conda install -c conda-forge 'ffmpeg<7'
brew install ffmpeg brew install ffmpeg
``` ```
#### 의존성 설치
```bash
pip install -r extra-req.txt --no-deps
pip install -r requirements.txt
```
### GPT-SoVITS 실행하기 (Docker 사용) ### GPT-SoVITS 실행하기 (Docker 사용)
#### Docker 이미지 선택 #### Docker 이미지 선택

34
docs/tr/README.md
View File

@ -59,31 +59,41 @@ Eğer bir Windows kullanıcısıysanız (win>=10 ile test edilmiştir), [entegre
### Linux ### Linux
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <CU124|CU128|ROCM|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### macOS ### macOS
**Not: Mac'lerde GPU'larla eğitilen modeller, diğer cihazlarda eğitilenlere göre önemli ölçüde daha düşük kalitede sonuç verir, bu nedenle geçici olarak CPU'lar kullanıyoruz.** **Not: Mac'lerde GPU'larla eğitilen modeller, diğer cihazlarda eğitilenlere göre önemli ölçüde daha düşük kalitede sonuç verir, bu nedenle geçici olarak CPU'lar kullanıyoruz.**
1. `xcode-select --install` komutunu çalıştırarak Xcode komut satırı araçlarını yükleyin. Aşağıdaki komutları çalıştırarak programı yükleyin:
2. Aşağıdaki komutları çalıştırarak programı yükleyin:
```bash ```bash
conda create -n GPTSoVits python=3.9 conda create -n GPTSoVits python=3.10
conda activate GPTSoVits conda activate GPTSoVits
bash install.sh --device <CU124|CU128|ROCM|MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5] bash install.sh --device <MPS|CPU> --source <HF|HF-Mirror|ModelScope> [--download-uvr5]
``` ```
### El ile Yükleme ### El ile Yükleme
#### Bağımlılıkları Yükleme
```bash
conda create -n GPTSoVits python=3.10
conda activate GPTSoVits
pip install -r extra-req.txt --no-deps
pip install -r requirements.txt
```
#### FFmpeg'i Yükleme #### FFmpeg'i Yükleme
##### Conda Kullanıcıları ##### Conda Kullanıcıları
```bash ```bash
conda activate GPTSoVits
conda install ffmpeg conda install ffmpeg
``` ```
@ -92,12 +102,13 @@ conda install ffmpeg
```bash ```bash
sudo apt install ffmpeg sudo apt install ffmpeg
sudo apt install libsox-dev sudo apt install libsox-dev
conda install -c conda-forge 'ffmpeg<7'
``` ```
##### Windows Kullanıcıları ##### Windows Kullanıcıları
[ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) ve [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) dosyalarını indirin ve GPT-SoVITS kök dizinine yerleştirin. [ffmpeg.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffmpeg.exe) ve [ffprobe.exe](https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/ffprobe.exe) dosyalarını indirin ve GPT-SoVITS kök dizinine yerleştirin
[Visual Studio 2017](https://aka.ms/vs/17/release/vc_redist.x86.exe) ortamını yükleyin
##### MacOS Kullanıcıları ##### MacOS Kullanıcıları
@ -105,13 +116,6 @@ conda install -c conda-forge 'ffmpeg<7'
brew install ffmpeg brew install ffmpeg
``` ```
#### Bağımlılıkları Yükleme
```bash
pip install -r extra-req.txt --no-deps
pip install -r requirements.txt
```
### GPT-SoVITS Çalıştırma (Docker Kullanarak) ### GPT-SoVITS Çalıştırma (Docker Kullanarak)
#### Docker İmajı Seçimi #### Docker İmajı Seçimi