Yaxin
/
live-digital-avatar-gptsovits
25
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

更新整合包，优化readme (#1145)

Browse Source 
* Update README

* Update README

* update README

* update README

* 优化

* fix

* 优化

* fix

* fix
main
Lion-Wu 1 year ago committed by GitHub
parent 54cdf84c0b
commit 87d39e8312
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 78 additions and 45 deletions
Show Stats Download Patch File Download Diff File

13
README.md
Unescape Escape View File

@ -12,8 +12,7 @@ A Powerful Few-shot Voice Conversion and Text-to-Speech WebUI.<br><br>
[![Huggingface](https://img.shields.io/badge/🤗%20-Models%20Repo-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/GPT-SoVITS/tree/main)
[![Discord](https://img.shields.io/discord/1198701940511617164?color=%23738ADB&label=Discord&style=for-the-badge)](https://discord.gg/dnrgs5GHfG)
[**English**](./README.md) | [**中文简体**](./docs/cn/README.md) | [**日本語**](./docs/ja/README.md) | [**한국어**](./docs/ko/README.md)
**English** | [**中文简体**](./docs/cn/README.md) | [**日本語**](./docs/ja/README.md) | [**한국어**](./docs/ko/README.md) | [**Türkçe**](./docs/tr/README.md)
</div>
@ -52,11 +51,11 @@ _Note: numba==0.56.4 requires py<3.11_
### Windows
If you are a Windows user (tested with win>=10), you can directly download the [pre-packaged distribution](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.
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.
Users in China region can download [the 0217 package](https://www.icloud.com.cn/iclouddrive/061bfkcVJcBfsMfLF5R2XKdTQ#GPT-SoVITS-beta0217) or [the 0306fix2 package](https://www.icloud.com.cn/iclouddrive/09aaTLf96aa92dbLe0fPNM5CQ#GPT-SoVITS-beta0306fix2) by clicking the links and then selecting "Download a copy."
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 0306fix2 version doubles the inference speed and fixes all issues with the no reference text mode._
_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._
### Linux
@ -198,7 +197,7 @@ D:\GPT-SoVITS\xxx/xxx.wav|xxx|en|I like playing Genshin.
- [ ] better sovits base model (enhanced audio quality)
- [ ] model mix
## (Optional) If you need, here will provide the command line operation mode
## (Additional) Method for running from the command line
Use the command line to open the WebUI for UVR5
```
python tools/uvr5/webui.py "<infer_device>" <is_half> <webui_port_uvr5>
@ -233,7 +232,7 @@ A custom list save path is enabled
Special thanks to the following projects and contributors:
### Theoretical
### Theoretical Research
- [ar-vits](https://github.com/innnky/ar-vits)
- [SoundStorm](https://github.com/yangdongchao/SoundStorm/tree/master/soundstorm/s1/AR)
- [vits](https://github.com/jaywalnut310/vits)

28
docs/cn/README.md
Unescape Escape View File

@ -10,8 +10,9 @@
[![Open In Colab](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge&logo=googlecolab&color=525252)](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
[![License](https://img.shields.io/badge/LICENSE-MIT-green.svg?style=for-the-badge)](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
[![Huggingface](https://img.shields.io/badge/🤗%20-Models%20Repo-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/GPT-SoVITS/tree/main)
[![Discord](https://img.shields.io/discord/1198701940511617164?color=%23738ADB&label=Discord&style=for-the-badge)](https://discord.gg/dnrgs5GHfG)
[**English**](../../README.md) | [**中文简体**](./README.md) | [**日本語**](../ja/README.md) | [**한국어**](../ko/README.md)
[**English**](../../README.md) | **中文简体** | [**日本語**](../ja/README.md) | [**한국어**](../ko/README.md) | [**Türkçe**](../tr/README.md)
</div>
@ -50,11 +51,11 @@ _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），可以直接下载[预打包文件](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。
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。
中国地区用户可以通过点击链接并选择“下载副本”来下载[0217版本包](https://www.icloud.com.cn/iclouddrive/061bfkcVJcBfsMfLF5R2XKdTQ#GPT-SoVITS-beta0217)或[0306fix2版本包](https://www.icloud.com.cn/iclouddrive/09aaTLf96aa92dbLe0fPNM5CQ#GPT-SoVITS-beta0306fix2)。
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：0306fix2版本推理速度翻倍，节约生命。修复了无参考文本模式的所有问题。_
_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_
### Linux
@ -148,7 +149,7 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
对于中文自动语音识别（附加），从 [Damo ASR Model](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/files), [Damo VAD Model](https://modelscope.cn/models/damo/speech_fsmn_vad_zh-cn-16k-common-pytorch/files), 和 [Damo Punc Model](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/files) 下载模型，并将它们放置在 `tools/asr/models` 中。
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。
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”)
@ -184,7 +185,7 @@ D:\GPT-SoVITS\xxx/xxx.wav|xxx|en|I like playing Genshin.
- [ ] 用户指南。
- [x] 日语和英语数据集微调训练。
- [ ] **Features:**
- [ ] **功能:**
- [ ] 零样本声音转换（5 秒）/ 少样本声音转换（1 分钟）。
- [ ] TTS 语速控制。
- [ ] 增强的 TTS 情感控制。
@ -196,7 +197,7 @@ D:\GPT-SoVITS\xxx/xxx.wav|xxx|en|I like playing Genshin.
- [ ] 更好的 sovits 基础模型（增强的音频质量）。
- [ ] 模型混合。
## （可选）命令行的操作方式
## （附加）命令行运行方式
使用命令行打开UVR5的WebUI
````
python tools/uvr5/webui.py "<infer_device>" <is_half> <webui_port_uvr5>
@ -226,24 +227,33 @@ python tools/asr/funasr_asr.py -i <input> -o <output>
python ./tools/asr/fasterwhisper_asr.py -i <input> -o <output> -l <language>
````
启用自定义列表保存路径
## 致谢
特别感谢以下项目和贡献者：
### 理论研究
- [ar-vits](https://github.com/innnky/ar-vits)
- [SoundStorm](https://github.com/yangdongchao/SoundStorm/tree/master/soundstorm/s1/AR)
- [vits](https://github.com/jaywalnut310/vits)
- [TransferTTS](https://github.com/hcy71o/TransferTTS/blob/master/models.py#L556)
- [Chinese Speech Pretrain](https://github.com/TencentGameMate/chinese_speech_pretrain)
- [contentvec](https://github.com/auspicious3000/contentvec/)
- [hifi-gan](https://github.com/jik876/hifi-gan)
- [Chinese-Roberta-WWM-Ext-Large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large)
- [fish-speech](https://github.com/fishaudio/fish-speech/blob/main/tools/llama/generate.py#L41)
### 预训练模型
- [Chinese Speech Pretrain](https://github.com/TencentGameMate/chinese_speech_pretrain)
- [Chinese-Roberta-WWM-Ext-Large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large)
### 推理用文本前端
- [paddlespeech zh_normalization](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/paddlespeech/t2s/frontend/zh_normalization)
- [LangSegment](https://github.com/juntaosun/LangSegment)
### WebUI 工具
- [ultimatevocalremovergui](https://github.com/Anjok07/ultimatevocalremovergui)
- [audio-slicer](https://github.com/openvpi/audio-slicer)
- [SubFix](https://github.com/cronrpc/SubFix)
- [FFmpeg](https://github.com/FFmpeg/FFmpeg)
- [gradio](https://github.com/gradio-app/gradio)
- [faster-whisper](https://github.com/SYSTRAN/faster-whisper)
- [FunASR](https://github.com/alibaba-damo-academy/FunASR)
## 感谢所有贡献者的努力

26
docs/ja/README.md
Unescape Escape View File

@ -10,8 +10,9 @@
[![Open In Colab](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge&logo=googlecolab&color=525252)](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
[![License](https://img.shields.io/badge/LICENSE-MIT-green.svg?style=for-the-badge)](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
[![Huggingface](https://img.shields.io/badge/🤗%20-Models%20Repo-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/GPT-SoVITS/tree/main)
[![Discord](https://img.shields.io/discord/1198701940511617164?color=%23738ADB&label=Discord&style=for-the-badge)](https://discord.gg/dnrgs5GHfG)
[**English**](../../README.md) | [**中文简体**](../cn/README.md) | [**日本語**](./README.md) | [**한국어**](../ko/README.md)
[**English**](../../README.md) | [**中文简体**](../cn/README.md) | **日本語** | [**한국어**](../ko/README.md) | [**Türkçe**](../tr/README.md)
</div>
@ -33,6 +34,8 @@
https://github.com/RVC-Boss/GPT-SoVITS/assets/129054828/05bee1fa-bdd8-4d85-9350-80c060ab47fb
**ユーザーマニュアル: [简体中文](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e) | [English](https://rentry.co/GPT-SoVITS-guide#/)**
## インストール
### テスト済みの環境
@ -46,7 +49,9 @@ _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）、[事前にパッケージ化されたディストリビューション](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true)を直接ダウンロードし、_go-webui.bat_ をダブルクリックして GPT-SoVITS-WebUI を起動することができます。
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。_
### Linux
@ -174,7 +179,7 @@ D:\GPT-SoVITS\xxx/xxx.wav|xxx|en|I like playing Genshin.
- [ ] より良い sovits ベースモデル（音質向上）
- [ ] モデルミックス
## (オプション) 必要に応じて、コマンドライン操作モードが提供されます。
## (追加の) コマンドラインから実行する方法
コマンド ラインを使用して UVR5 の WebUI を開きます
```
python tools/uvr5/webui.py "<infer_device>" <is_half> <webui_port_uvr5>
@ -204,24 +209,33 @@ ASR処理はFaster_Whisperを通じて実行されます(中国語を除くASR
python ./tools/asr/fasterwhisper_asr.py -i <input> -o <output> -l <language>
```
カスタムリストの保存パスが有効になっています
## クレジット
以下のプロジェクトとコントリビューターに感謝します:
特に以下のプロジェクトと貢献者に感謝します：
### 理論研究
- [ar-vits](https://github.com/innnky/ar-vits)
- [SoundStorm](https://github.com/yangdongchao/SoundStorm/tree/master/soundstorm/s1/AR)
- [vits](https://github.com/jaywalnut310/vits)
- [TransferTTS](https://github.com/hcy71o/TransferTTS/blob/master/models.py#L556)
- [Chinese Speech Pretrain](https://github.com/TencentGameMate/chinese_speech_pretrain)
- [contentvec](https://github.com/auspicious3000/contentvec/)
- [hifi-gan](https://github.com/jik876/hifi-gan)
- [Chinese-Roberta-WWM-Ext-Large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large)
- [fish-speech](https://github.com/fishaudio/fish-speech/blob/main/tools/llama/generate.py#L41)
### 事前学習モデル
- [Chinese Speech Pretrain](https://github.com/TencentGameMate/chinese_speech_pretrain)
- [Chinese-Roberta-WWM-Ext-Large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large)
### 推論用テキストフロントエンド
- [paddlespeech zh_normalization](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/paddlespeech/t2s/frontend/zh_normalization)
- [LangSegment](https://github.com/juntaosun/LangSegment)
### WebUI ツール
- [ultimatevocalremovergui](https://github.com/Anjok07/ultimatevocalremovergui)
- [audio-slicer](https://github.com/openvpi/audio-slicer)
- [SubFix](https://github.com/cronrpc/SubFix)
- [FFmpeg](https://github.com/FFmpeg/FFmpeg)
- [gradio](https://github.com/gradio-app/gradio)
- [faster-whisper](https://github.com/SYSTRAN/faster-whisper)
- [FunASR](https://github.com/alibaba-damo-academy/FunASR)
## すべてのコントリビューターに感謝します

27
docs/ko/README.md
Unescape Escape View File

@ -10,8 +10,9 @@
[![Open In Colab](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge&logo=googlecolab&color=525252)](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
[![License](https://img.shields.io/badge/LICENSE-MIT-green.svg?style=for-the-badge)](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
[![Huggingface](https://img.shields.io/badge/🤗%20-Models%20Repo-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/GPT-SoVITS/tree/main)
[![Discord](https://img.shields.io/discord/1198701940511617164?color=%23738ADB&label=Discord&style=for-the-badge)](https://discord.gg/dnrgs5GHfG)
[**English**](../../README.md) | [**中文简体**](../cn/README.md) | [**日本語**](../ja/README.md) | [**한국어**](./README.md)
[**English**](../../README.md) | [**中文简体**](../cn/README.md) | [**日本語**](../ja/README.md) | **한국어** | [**Türkçe**](../tr/README.md)
</div>
@ -33,6 +34,8 @@
https://github.com/RVC-Boss/GPT-SoVITS/assets/129054828/05bee1fa-bdd8-4d85-9350-80c060ab47fb
**사용자 설명서: [简体中文](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e) | [English](https://rentry.co/GPT-SoVITS-guide#/)**
## 설치
### 테스트 통과 환경
@ -46,7 +49,9 @@ _참고: numba==0.56.4 는 python<3.11 을 필요로 합니다._
### Windows
Windows 사용자이며 (win>=10에서 테스트 완료) [미리 패키지된 배포판](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true)을 직접 다운로드하여 _go-webui.bat_을 더블클릭하면 GPT-SoVITS-WebUI를 시작할 수 있습니다.
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._
### Linux
@ -178,7 +183,7 @@ D:\GPT-SoVITS\xxx/xxx.wav|xxx|en|I like playing Genshin.
- [ ] 더 나은 sovits 기본 모델 (향상된 오디오 품질).
- [ ] 모델 블렌딩.
## (선택 사항) 필요한 경우 여기에서 명령줄 작업 모드를 제공합니다.
## (추가적인) 명령줄에서 실행하는 방법
명령줄을 사용하여 UVR5용 WebUI 열기
```
python tools/uvr5/webui.py "<infer_device>" <is_half> <webui_port_uvr5>
@ -208,24 +213,34 @@ ASR 처리는 Faster_Whisper(중국어를 제외한 ASR 마킹)를 통해 수행
python ./tools/asr/fasterwhisper_asr.py -i <input> -o <output> -l <language>
```
사용자 정의 목록 저장 경로가 활성화되었습니다.
## 감사의 말
특별히 다음 프로젝트와 기여자에게 감사드립니다:
다음 프로젝트와 기여자들에게 특별히 감사드립니다:
### 이론 연구
- [ar-vits](https://github.com/innnky/ar-vits)
- [SoundStorm](https://github.com/yangdongchao/SoundStorm/tree/master/soundstorm/s1/AR)
- [vits](https://github.com/jaywalnut310/vits)
- [TransferTTS](https://github.com/hcy71o/TransferTTS/blob/master/models.py#L556)
- [Chinese Speech Pretrain](https://github.com/TencentGameMate/chinese_speech_pretrain)
- [contentvec](https://github.com/auspicious3000/contentvec/)
- [hifi-gan](https://github.com/jik876/hifi-gan)
- [Chinese-Roberta-WWM-Ext-Large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large)
- [fish-speech](https://github.com/fishaudio/fish-speech/blob/main/tools/llama/generate.py#L41)
### 사전 학습 모델
- [Chinese Speech Pretrain](https://github.com/TencentGameMate/chinese_speech_pretrain)
- [Chinese-Roberta-WWM-Ext-Large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large)
### 추론용 텍스트 프론트엔드
- [paddlespeech zh_normalization](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/paddlespeech/t2s/frontend/zh_normalization)
- [LangSegment](https://github.com/juntaosun/LangSegment)
### WebUI 도구
- [ultimatevocalremovergui](https://github.com/Anjok07/ultimatevocalremovergui)
- [audio-slicer](https://github.com/openvpi/audio-slicer)
- [SubFix](https://github.com/cronrpc/SubFix)
- [FFmpeg](https://github.com/FFmpeg/FFmpeg)
- [gradio](https://github.com/gradio-app/gradio)
- [faster-whisper](https://github.com/SYSTRAN/faster-whisper)
- [FunASR](https://github.com/alibaba-damo-academy/FunASR)
## 모든 기여자들에게 감사드립니다 ;)

29
docs/tr/README.md
Unescape Escape View File

@ -12,8 +12,7 @@ Güçlü Birkaç Örnekli Ses Dönüştürme ve Metinden Konuşmaya Web Arayüz
[![Huggingface](https://img.shields.io/badge/🤗%20-Models%20Repo-yellow.svg?style=for-the-badge)](https://huggingface.co/lj1995/GPT-SoVITS/tree/main)
[![Discord](https://img.shields.io/discord/1198701940511617164?color=%23738ADB&label=Discord&style=for-the-badge)](https://discord.gg/dnrgs5GHfG)
[**İngilizce**](./README.md) | [**Çince (Basitleştirilmiş)**](./docs/cn/README.md) | [**Japonca**](./docs/ja/README.md) | [**Korece**](./docs/ko/README.md)
[**English**](../../README.md) | [**中文简体**](../cn/README.md) | [**日本語**](../ja/README.md) | [**한국어**](../ko/README.md) | **Türkçe**
</div>
@ -35,12 +34,10 @@ Görünmeyen konuşmacılar birkaç örnekli ince ayar demosu:
https://github.com/RVC-Boss/GPT-SoVITS/assets/129054828/05bee1fa-bdd8-4d85-9350-80c060ab47fb
**Kullanıcı kılavuzu: [Basitleştirilmiş Çince](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e) | [İngilizce](https://rentry.co/GPT-SoVITS-guide#/)**
**Kullanıcı Kılavuzu: [简体中文](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e) | [English](https://rentry.co/GPT-SoVITS-guide#/)**
## Kurulum
Çin bölgesindeki kullanıcılar için, tam işlevselliği çevrimiçi olarak deneyimlemek üzere AutoDL Bulut Docker'ı kullanmak için [buraya tıklayabilirsiniz](https://www.codewithgpu.com/i/RVC-Boss/GPT-SoVITS/GPT-SoVITS-Official).
### Test Edilmiş Ortamlar
- Python 3.9, PyTorch 2.0.1, CUDA 11
@ -52,11 +49,9 @@ _Not: numba==0.56.4, py<3.11 gerektirir_
### Windows
Bir Windows kullanıcısıysanız (win>=10 ile test edilmiştir), [önceden paketlenmiş dağıtımı](https://huggingface.co/lj1995/GPT-SoVITS-windows-package/resolve/main/GPT-SoVITS-beta.7z?download=true) indirebilir ve GPT-SoVITS-WebUI'yi başlatmak için _go-webui.bat_ dosyasını çift tıklayabilirsiniz.
Çin bölgesindeki kullanıcılar, aşağıdaki bağlantılara tıklayıp "Bir kopya indir"i seçerek [0217 paketini](https://www.icloud.com.cn/iclouddrive/061bfkcVJcBfsMfLF5R2XKdTQ#GPT-SoVITS-beta0217) veya [0306fix2 paketini](https://www.icloud.com.cn/iclouddrive/09aaTLf96aa92dbLe0fPNM5CQ#GPT-SoVITS-beta0306fix2) indirebilirler.
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: 0306fix2 sürümü çıkarım hızını iki katına çıkarır ve referans metni olmayan moddaki tüm sorunları giderir._
_Not: 0206 sürümünün çıkarım hızı daha hızlıdır, 0217 yeni sürümünün çıkarım kalitesi ise daha iyidir. İhtiyacınıza göre seçim yapabilirsiniz._
### Linux
@ -198,7 +193,7 @@ D:\GPT-SoVITS\xxx/xxx.wav|xxx|en|I like playing Genshin.
- [ ] daha iyi sovits temel modeli (geliştirilmiş ses kalitesi)
- [ ] model karışımı
## (İsteğe Bağlı) İhtiyacınız varsa, burada komut satırı işlem modu sağlanacaktır
## (Ekstra) Komut satırından çalıştırma yöntemi
UVR5 için Web Arayüzünü açmak için komut satırını kullanın
```
python tools/uvr5/webui.py "<infer_device>" <is_half> <webui_port_uvr5>
@ -229,11 +224,11 @@ python ./tools/asr/fasterwhisper_asr.py -i <girdi> -o <çıktı> -l <dil>
```
Özel bir liste kaydetme yolu etkinleştirildi
## Teşekkürler
## Katkı Verenler
Aşağıdaki projeler ve katkıda bulunanlara özel teşekkürler:
Özellikle aşağıdaki projelere ve katkıda bulunanlara teşekkür ederiz:
### Teorik
### Teorik Araştırma
- [ar-vits](https://github.com/innnky/ar-vits)
- [SoundStorm](https://github.com/yangdongchao/SoundStorm/tree/master/soundstorm/s1/AR)
- [vits](https://github.com/jaywalnut310/vits)
@ -242,12 +237,12 @@ Aşağıdaki projeler ve katkıda bulunanlara özel teşekkürler:
- [hifi-gan](https://github.com/jik876/hifi-gan)
- [fish-speech](https://github.com/fishaudio/fish-speech/blob/main/tools/llama/generate.py#L41)
### Önceden Eğitilmiş Modeller
- [Çince Konuşma Ön Eğitimi](https://github.com/TencentGameMate/chinese_speech_pretrain)
- [Çince-Roberta-WWM-Ext-Large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large)
### Çıkarım için Metin Ön Ucu
- [Chinese Speech Pretrain](https://github.com/TencentGameMate/chinese_speech_pretrain)
- [Chinese-Roberta-WWM-Ext-Large](https://huggingface.co/hfl/chinese-roberta-wwm-ext-large)
### Tahmin İçin Metin Ön Ucu
- [paddlespeech zh_normalization](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/paddlespeech/t2s/frontend/zh_normalization)
- [LangSegment](https://github.com/juntaosun/LangSegment)
### Web Arayüzü Araçları
### WebUI Araçları
- [ultimatevocalremovergui](https://github.com/Anjok07/ultimatevocalremovergui)
- [audio-slicer](https://github.com/openvpi/audio-slicer)
- [SubFix](https://github.com/cronrpc/SubFix)

Write Preview
Loading…
Cancel
Save