blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2025-04-05 19:41:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update README (#1291)

Browse Source 
* update README

* update README
This commit is contained in:
Lion-Wu 2024-07-11 17:54:56 +08:00 committed by GitHub
parent 368045c94e
commit d65f0ff8b4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 50 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
README.md
View File

@ -38,7 +38,7 @@ https://github.com/RVC-Boss/GPT-SoVITS/assets/129054828/05bee1fa-bdd8-4d85-9350-
## Installation
For users in China region, you can [click here](https://www.codewithgpu.com/i/RVC-Boss/GPT-SoVITS/GPT-SoVITS-Official) to use AutoDL Cloud Docker to experience the full functionality online.
For users in the China region, you can [click here](https://www.codewithgpu.com/i/RVC-Boss/GPT-SoVITS/GPT-SoVITS-Official) to use AutoDL Cloud Docker to experience the full functionality online.
### Tested Environments
@ -51,11 +51,9 @@ _Note: numba==0.56.4 requires py<3.11_
### Windows
If you are a Windows user (tested with win>=10), you can download [the 0206fix3 packedge](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta-fast-inference-branch.7z?download=true) or [the 0217fix2 packedge](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta0217fix2.7z?download=true) and double-click on _go-webui.bat_ to start GPT-SoVITS-WebUI.
If you are a Windows user (tested with win>=10), you can [download the integrated package](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true) and double-click on _go-webui.bat_ to start GPT-SoVITS-WebUI.
Users in China region can download [the 0206fix3 package](https://www.icloud.com.cn/iclouddrive/075NNKIRC2zqnWn-9rhD63WGA#GPT-SoVITS-beta0206fix3) or [the 0217fix2 package](https://www.icloud.com.cn/iclouddrive/091QHaIbZMDZYQg7IX3g2kCqg#GPT-SoVITS-beta0217fix2) by clicking the links and then selecting "Download a copy." (Log out if you encounter errors while downloading.)
_Note: The inference speed of version 0206 is faster, while the inference quality of the new 0217 version is better. You can choose according to your needs._
Users in the China region can [download the package](https://www.icloud.com.cn/iclouddrive/030K8WjGJ9xMXhpzJVIMEWPzQ#GPT-SoVITS-beta0706fix1) by clicking the link and then selecting "Download a copy." (Log out if you encounter errors while downloading.)
### Linux
@ -69,8 +67,8 @@ bash install.sh
**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`
2. Install FFmpeg by running `brew install ffmpeg` or `conda install ffmpeg`.
1. Install Xcode command-line tools by running `xcode-select --install`.
2. Install FFmpeg by running `brew install ffmpeg`.
3. Install the program by running the following commands:
```bash
@ -108,6 +106,11 @@ conda install -c conda-forge 'ffmpeg<7'
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.
##### Mac Users
```bash
brew install ffmpeg
```
### Using Docker
#### docker-compose.yaml configuration
@ -141,7 +144,7 @@ Download pretrained models from [GPT-SoVITS Models](https://huggingface.co/lj199
For UVR5 (Vocals/Accompaniment Separation & Reverberation Removal, additionally), download models from [UVR5 Weights](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/uvr5_weights) and place them in `tools/uvr5/uvr5_weights`.
Users in China region can download these two models by entering the links below and clicking "Download a copy"
Users in the China region can download these two models by entering the links below and clicking "Download a copy"(Log out if you encounter errors while downloading.)
- [GPT-SoVITS Models](https://www.icloud.com.cn/iclouddrive/056y_Xog_HXpALuVUjscIwTtg#GPT-SoVITS_Models)
@ -151,9 +154,9 @@ For Chinese ASR (additionally), download models from [Damo ASR Model](https://mo
For English or Japanese ASR (additionally), download models from [Faster Whisper Large V3](https://huggingface.co/Systran/faster-whisper-large-v3) and place them in `tools/asr/models`. Also, [other models](https://huggingface.co/Systran) may have the similar effect with smaller disk footprint.
Users in China region can download this model by entering the links below
Users in the China region can download this model by entering the links below
- [Faster Whisper Large V3](https://www.icloud.com/iclouddrive/0c4pQxFs7oWyVU1iMTq2DbmLA#faster-whisper-large-v3) (clicking "Download a copy")
- [Faster Whisper Large V3](https://www.icloud.com/iclouddrive/0c4pQxFs7oWyVU1iMTq2DbmLA#faster-whisper-large-v3) (Click "Download a copy", log out if you encounter errors while downloading.)
- [Faster Whisper Large V3](https://hf-mirror.com/Systran/faster-whisper-large-v3) (HuggingFace mirror site)

25
docs/cn/README.md
View File

@ -51,11 +51,9 @@ _注: numba==0.56.4 需要 python<3.11_
### Windows
如果你是 Windows 用户（已在 win>=10 上测试），可以下载[0206fix3 整合包](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta-fast-inference-branch.7z?download=true)或[0217fix2 整合包](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta0217fix2.7z?download=true)，解压后双击 go-webui.bat 即可启动 GPT-SoVITS-WebUI。
如果你是 Windows 用户（已在 win>=10 上测试），可以下载[下载整合包](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true)，解压后双击 go-webui.bat 即可启动 GPT-SoVITS-WebUI。
中国地区用户可以通过点击链接并选择“下载副本”来下载[0206fix3 整合包](https://www.icloud.com.cn/iclouddrive/075NNKIRC2zqnWn-9rhD63WGA#GPT-SoVITS-beta0206fix3)或[0217fix2 整合包](https://www.icloud.com.cn/iclouddrive/091QHaIbZMDZYQg7IX3g2kCqg#GPT-SoVITS-beta0217fix2)。(如果下载时遇到错误，请退出登录)
_注：0206版本的推理速度更快，0217新版的推理效果更好，可按需选择_
中国地区用户可以通过点击链接并选择“下载副本”[下载整合包](https://www.icloud.com.cn/iclouddrive/030K8WjGJ9xMXhpzJVIMEWPzQ#GPT-SoVITS-beta0706fix1)。（如果下载时遇到错误，请退出登录）
### Linux
@ -67,10 +65,10 @@ bash install.sh
### 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。
2. 运行 `brew install ffmpeg` 或 `conda install ffmpeg` 安装 FFmpeg。
2. 运行 `brew install ffmpeg` 安装 FFmpeg。
3. 完成上述步骤后，运行以下的命令来安装本项目：
```bash
@ -90,13 +88,13 @@ pip install -r requirements.txt
#### 安装 FFmpeg
##### Conda 使用者
##### Conda 用户
```bash
conda install ffmpeg
```
##### Ubuntu/Debian 使用者
##### Ubuntu/Debian 用户
```bash
sudo apt install ffmpeg
@ -104,10 +102,15 @@ sudo apt install libsox-dev
conda install -c conda-forge 'ffmpeg<7'
```
##### Windows 使用者
##### 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。
##### Mac 用户
```bash
brew install ffmpeg
```
### 在 Docker 中使用
#### docker-compose.yaml 设置
@ -141,7 +144,7 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
对于 UVR5（人声/伴奏分离和混响移除，附加），从 [UVR5 Weights](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/uvr5_weights) 下载模型，并将它们放置在 `tools/uvr5/uvr5_weights` 中。
中国地区用户可以进入以下链接并点击“下载副本”下载以上两个模型：
中国地区用户可以进入以下链接并点击“下载副本”下载以上两个模型（如果下载时遇到错误，请退出登录）：
- [GPT-SoVITS Models](https://www.icloud.com.cn/iclouddrive/056y_Xog_HXpALuVUjscIwTtg#GPT-SoVITS_Models)
@ -152,7 +155,7 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
对于英语与日语自动语音识别（附加）,从 [Faster Whisper Large V3](https://huggingface.co/Systran/faster-whisper-large-v3) 下载模型，并将它们放置在 `tools/asr/models` 中。 此外，[其他模型](https://huggingface.co/Systran)可能具有类似效果，但占用更小的磁盘空间。
中国地区用户可以通过以下链接下载：
- [Faster Whisper Large V3](https://www.icloud.com/iclouddrive/0c4pQxFs7oWyVU1iMTq2DbmLA#faster-whisper-large-v3)(点击“下载副本”)
- [Faster Whisper Large V3](https://www.icloud.com/iclouddrive/0c4pQxFs7oWyVU1iMTq2DbmLA#faster-whisper-large-v3)（点击“下载副本”，如果下载时遇到错误，请退出登录）
- [Faster Whisper Large V3](https://hf-mirror.com/Systran/faster-whisper-large-v3)(Hugging Face镜像站)

11
docs/ja/README.md
View File

@ -49,9 +49,7 @@ _注記: numba==0.56.4 は py<3.11 が必要です_
### Windows
Windows ユーザーの場合（win>=10 でテスト済み）、[0206fix3 パッケージ](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta-fast-inference-branch.7z?download=true) または [0217fix2 パッケージ](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta0217fix2.7z?download=true) をダウンロードして、解凍後に _go-webui.bat_ をダブルクリックするだけで GPT-SoVITS-WebUI を起動できます。
_注：0206バージョンの推論速度は速いですが、0217の新バージョンの推論品質は優れています。必要に応じて選択してください。_
Windows ユーザーの方へ（Windows 10 以降でテスト済み）、[統合パッケージをダウンロード](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true)し、解凍後に _go-webui.bat_ をダブルクリックすると、GPT-SoVITS-WebUI が起動します。
### Linux
@ -66,7 +64,7 @@ bash install.sh
**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。
2. `brew install ffmpeg` または `conda install ffmpeg` を実行して、FFmpegをインストールします。
2. `brew install ffmpeg` を実行してFFmpegをインストールします。
3. 上記の手順を完了した後、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
@ -104,6 +102,11 @@ conda install -c conda-forge 'ffmpeg<7'
[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 のルートディレクトリに置きます。
##### Mac ユーザー
```bash
brew install ffmpeg
```
### Docker の使用
#### docker-compose.yaml の設定

11
docs/ko/README.md
View File

@ -49,9 +49,7 @@ _참고: numba==0.56.4 는 python<3.11 을 필요로 합니다._
### Windows
Windows 사용자라면 (win>=10에서 테스트됨), [0206fix3 패키지](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta-fast-inference-branch.7z?download=true) 또는 [0217fix2 패키지](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta0217fix2.7z?download=true)를 다운로드하고 압축을 풀어 _go-webui.bat_ 파일을 더블 클릭하면 GPT-SoVITS-WebUI를 시작할 수 있습니다.
_참고: 0206 버전은 추론 속도가 더 빠르지만, 0217 새 버전은 추론 품질이 더 좋습니다. 필요에 따라 선택할 수 있습니다._
Windows 사용자라면 (win>=10에서 테스트됨), [통합 패키지를 다운로드](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true)한 후 압축을 풀고 _go-webui.bat_ 파일을 더블 클릭하면 GPT-SoVITS-WebUI를 시작할 수 있습니다.
### Linux
@ -66,7 +64,7 @@ bash install.sh
**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.
2. `brew install ffmpeg` 또는 `conda install ffmpeg`을 실행하여 FFmpeg를 설치하세요.
2. `brew install ffmpeg` 명령어를 실행하여 FFmpeg를 설치합니다.
3. 위의 단계를 완료한 후, 다음 명령어를 실행하여 이 프로젝트를 설치하세요.
```bash
@ -104,6 +102,11 @@ conda install -c conda-forge 'ffmpeg<7'
[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.
##### Mac 사용자
```bash
brew install ffmpeg
```
### Docker에서 사용
#### docker-compose.yaml 설정

27
docs/tr/README.md
View File

@ -49,9 +49,7 @@ _Not: numba==0.56.4, py<3.11 gerektirir_
### Windows
Eğer bir Windows kullanıcısıysanız (win>=10 ile test edilmiştir), [0206fix3 paketini](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta-fast-inference-branch.7z?download=true) veya [0217fix2 paketini](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta0217fix2.7z?download=true) indirip _go-webui.bat_ dosyasına çift tıklayarak GPT-SoVITS-WebUI'yi başlatabilirsiniz.
_Not: 0206 sürümünün çıkarım hızı daha hızlıdır, 0217 yeni sürümünün çıkarım kalitesi ise daha iyidir. İhtiyacınıza göre seçim yapabilirsiniz._
Eğer bir Windows kullanıcısıysanız (win>=10 ile test edilmiştir), [entegre paketi indirin](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true) ve _go-webui.bat_ dosyasına çift tıklayarak GPT-SoVITS-WebUI'yi başlatın.
### Linux
@ -65,8 +63,8 @@ bash install.sh
**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
2. `brew install ffmpeg` veya `conda install ffmpeg` komutunu çalıştırarak FFmpeg'i yükleyin.
1. `xcode-select --install` komutunu çalıştırarak Xcode komut satırı araçlarını yükleyin.
2. FFmpeg'i yüklemek için `brew install ffmpeg` komutunu çalıştırın.
3. Aşağıdaki komutları çalıştırarak programı yükleyin:
```bash
@ -104,6 +102,11 @@ conda install -c conda-forge 'ffmpeg<7'
[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.
##### Mac Kullanıcıları
```bash
brew install ffmpeg
```
### Docker Kullanarak
#### docker-compose.yaml yapılandırması
@ -137,21 +140,9 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
UVR5 (Vokal/Eşlik Ayırma ve Yankı Giderme, ayrıca) için, modelleri [UVR5 Ağırlıkları](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/uvr5_weights) adresinden indirin ve `tools/uvr5/uvr5_weights` dizinine yerleştirin.
Çin bölgesindeki kullanıcılar, aşağıdaki bağlantıları girerek ve "Bir kopya indir"i tıklayarak bu iki modeli indirebilirler
- [GPT-SoVITS Modelleri](https://www.icloud.com.cn/iclouddrive/056y_Xog_HXpALuVUjscIwTtg#GPT-SoVITS_Models)
- [UVR5 Ağırlıkları](https://www.icloud.com.cn/iclouddrive/0bekRKDiJXboFhbfm3lM2fVbA#UVR5_Weights)
Çince ASR (ayrıca) için, modelleri [Damo ASR Modeli](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/files), [Damo VAD Modeli](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/files), ve [Damo Punc Modeli](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/files) adreslerinden indirin ve `tools/asr/models` dizinine yerleştirin.
İngilizce veya Japonca ASR (ayrıca) için, modelleri [Faster Whisper Large V3](https://huggingface.co/Systran/faster-whisper-large-v3) adresinden indirin ve `tools/asr/models` dizinine yerleştirin. Ayrıca, [diğer modeller](https://huggingface.co/Systran) daha küçük disk alanı kaplamasıyla benzer etkiye sahip olabilir.
Çin bölgesindeki kullanıcılar, aşağıdaki bağlantıları girerek bu modeli indirebilirler
- [Faster Whisper Large V3](https://www.icloud.com/iclouddrive/0c4pQxFs7oWyVU1iMTq2DbmLA#faster-whisper-large-v3) ("Bir kopya indir"i tıklayarak)
- [Faster Whisper Large V3](https://hf-mirror.com/Systran/faster-whisper-large-v3) (HuggingFace ayna sitesi)
İngilizce veya Japonca ASR (ayrıca) için, modelleri [Faster Whisper Large V3](https://huggingface.co/Systran/faster-whisper-large-v3) adresinden indirin ve `tools/asr/models` dizinine yerleştirin. Ayrıca, [diğer modeller](https://huggingface.co/Systran) daha küçük disk alanı kaplamasıyla benzer etkiye sahip olabilir.
## Veri Seti Formatı