From c60e796452650f15d1b8b45cc428226597397286 Mon Sep 17 00:00:00 2001
From: Lion-Wu <130235128+Lion-Wu@users.noreply.github.com>
Date: Mon, 12 Aug 2024 10:47:02 +0800
Subject: [PATCH] Update README (#1423)
Update README (#1423)
---
README.md | 48 +++++++------------
docs/cn/README.md | 62 ++++++++++--------------
docs/ja/README.md | 119 ++++++++++++++++++++++++++++++++++++++-------
docs/ko/README.md | 120 +++++++++++++++++++++++++++++++++++++++-------
docs/tr/README.md | 116 +++++++++++++++++++++++++++++++++++++-------
5 files changed, 348 insertions(+), 117 deletions(-)
diff --git a/README.md b/README.md
index 98fc0d0..91f1570 100644
--- a/README.md
+++ b/README.md
@@ -38,7 +38,7 @@ https://github.com/RVC-Boss/GPT-SoVITS/assets/129054828/05bee1fa-bdd8-4d85-9350-
## Installation
-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.
+For users in China, 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
@@ -53,7 +53,7 @@ _Note: numba==0.56.4 requires py<3.11_
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 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.)
+**Users in China can [download the package here](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e/dkxgpiy9zb96hob4#KTvnO).**
### Linux
@@ -141,31 +141,17 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
## Pretrained Models
-Download pretrained models from [GPT-SoVITS Models](https://huggingface.co/lj1995/GPT-SoVITS) and place them in `GPT_SoVITS/pretrained_models`.
+**Users in China can [download all these models here](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e/dkxgpiy9zb96hob4#nVNhX).**
-Download G2PW models from [G2PWModel-v2-onnx.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip), unzip and rename to `G2PWModel`, and then place them in `GPT_SoVITS\text`.(Chinese TTS Only)
+1. Download pretrained models from [GPT-SoVITS Models](https://huggingface.co/lj1995/GPT-SoVITS) and place them in `GPT_SoVITS/pretrained_models`.
-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`.
+2. Download G2PW models from [G2PWModel_1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip), unzip and rename to `G2PWModel`, and then place them in `GPT_SoVITS/text`.(Chinese TTS Only)
-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.)
+3. 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`.
-- [GPT-SoVITS Models](https://www.icloud.com/iclouddrive/044boFMiOHHt22SNr-c-tirbA#pretrained_models)
+4. For Chinese ASR (additionally), download models from [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), and [Damo Punc Model](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/files) and place them in `tools/asr/models`.
-- [UVR5 Weights](https://www.icloud.com.cn/iclouddrive/0bekRKDiJXboFhbfm3lM2fVbA#UVR5_Weights)
-
-- [G2PWModel_1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip)(Download G2PW models, unzip and rename to `G2PWModel`, and then place them in `GPT_SoVITS\text`.
-
-For Chinese ASR (additionally), download models from [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), and [Damo Punc Model](https://modelscope.cn/models/damo/punc_ct-transformer_zh-cn-common-vocab272727-pytorch/files) and place them in `tools/asr/models`.
-
-Or Download FunASR Model from [FunASR Model](https://www.icloud.com/iclouddrive/0b52_7SQWYr75kHkPoPXgpeQA#models), unzip and replace `tools/asr/models`.(Log out if you encounter errors while downloading.)
-
-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 the China region can download this model by entering the links below
-
-- [Faster Whisper Large V3](https://www.icloud.com/iclouddrive/00bUEp9_mcjMq_dhHu_vrAFDQ#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)
+5. 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.
## Dataset Format
@@ -249,25 +235,25 @@ then open the inference webui at `1-GPT-SoVITS-TTS/1C-inference`
New Features:
- 1.Support Korean and Cantonese
+1. Support Korean and Cantonese
- 2.An optimized text frontend
+2. An optimized text frontend
- 3.Pre-trained model extended from 2k hours to 5k hours
+3. Pre-trained model extended from 2k hours to 5k hours
- 4.Improved synthesis quality for low-quality reference audio
+4. Improved synthesis quality for low-quality reference audio
- [more details](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90v2%E2%80%90features-(%E6%96%B0%E7%89%B9%E6%80%A7) )
+ [more details](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90v2%E2%80%90features-(%E6%96%B0%E7%89%B9%E6%80%A7) )
Use v2 from v1 environment:
- 1.pip install -r requirements.txt to update some packages
+1. `pip install -r requirements.txt` to update some packages
- 2.clone the latest codes from github
+2. Clone the latest codes from github.
- 3.download v2 pretrained models from [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main/gsv-v2final-pretrained) and put them into GPT_SoVITS\pretrained_models\gsv-v2final-pretrained
+3. Download v2 pretrained models from [huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main/gsv-v2final-pretrained) and put them into `GPT_SoVITS\pretrained_models\gsv-v2final-pretrained`.
- Chinese v2 additional: [G2PWModel_1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip)(Download G2PW models, unzip and rename to `G2PWModel`, and then place them in `GPT_SoVITS\text`.
+ Chinese v2 additional: [G2PWModel_1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip)(Download G2PW models, unzip and rename to `G2PWModel`, and then place them in `GPT_SoVITS/text`.
## Todo List
diff --git a/docs/cn/README.md b/docs/cn/README.md
index ea67f9d..8c86b48 100644
--- a/docs/cn/README.md
+++ b/docs/cn/README.md
@@ -38,7 +38,7 @@ https://github.com/RVC-Boss/GPT-SoVITS/assets/129054828/05bee1fa-bdd8-4d85-9350-
## 安装
-中国地区用户可[点击此处](https://www.codewithgpu.com/i/RVC-Boss/GPT-SoVITS/GPT-SoVITS-Official)使用 AutoDL 云端镜像进行体验。
+中国地区的用户可[点击此处](https://www.codewithgpu.com/i/RVC-Boss/GPT-SoVITS/GPT-SoVITS-Official)使用 AutoDL 云端镜像进行体验。
### 测试通过的环境
@@ -53,7 +53,7 @@ _注: numba==0.56.4 需要 python<3.11_
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”[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)
+**中国地区的用户可以[在此处下载整合包](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e/dkxgpiy9zb96hob4#KTvnO)。**
### Linux
@@ -141,31 +141,17 @@ docker run --rm -it --gpus=all --env=is_half=False --volume=G:\GPT-SoVITS-Docker
## 预训练模型
-从 [GPT-SoVITS Models](https://huggingface.co/lj1995/GPT-SoVITS) 下载预训练模型,并将它们放置在 `GPT_SoVITS\pretrained_models` 中。
+**中国地区的用户可以[在此处下载这些模型](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e/dkxgpiy9zb96hob4#nVNhX)。**
-从 [G2PWModel-v2-onnx.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) 下载G2PW模型,并将它们解压重命名为`G2PWModel` 后放置在 `GPT_SoVITS\text` 中。(仅限中文TTS)
+1. 从 [GPT-SoVITS Models](https://huggingface.co/lj1995/GPT-SoVITS) 下载预训练模型,并将其放置在 `GPT_SoVITS/pretrained_models` 目录中。
-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。
+2. 从 [G2PWModel_1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip) 下载模型,解压并重命名为 `G2PWModel`,然后将其放置在 `GPT_SoVITS/text` 目录中。(仅限中文TTS)
-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):
+3. 对于 UVR5(人声/伴奏分离和混响移除,额外功能),从 [UVR5 Weights](https://huggingface.co/lj1995/VoiceConversionWebUI/tree/main/uvr5_weights) 下载模型,并将其放置在 `tools/uvr5/uvr5_weights` 目录中。
-- [GPT-SoVITS Models](https://www.icloud.com/iclouddrive/044boFMiOHHt22SNr-c-tirbA#pretrained_models)
-
-- [UVR5 Weights](https://www.icloud.com.cn/iclouddrive/0bekRKDiJXboFhbfm3lM2fVbA#UVR5_Weights)
-
-- [G2PWModel_1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip)(下载G2PW模型,并将它们解压重命名为 `G2PWModel` 后放置在 `GPT_SoVITS\text` 中)
-
-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。
-
-或者从[FunASR模型链接](https://www.icloud.com/iclouddrive/0b52_7SQWYr75kHkPoPXgpeQA#models)下载模型,并将它们解压后替换 `tools/asr/models` 。(点击“下载副本”,如果下载时遇到错误,请退出登录)
-
-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/00bUEp9_mcjMq_dhHu_vrAFDQ#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)
+4. 对于中文 ASR(额外功能),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` 目录中。
+5. 对于英语或日语 ASR(额外功能),从 [Faster Whisper Large V3](https://huggingface.co/Systran/faster-whisper-large-v3) 下载模型,并将其放置在 `tools/asr/models` 目录中。此外,[其他模型](https://huggingface.co/Systran) 可能具有类似效果且占用更少的磁盘空间。
## 数据集格式
@@ -249,44 +235,44 @@ python webui.py
新特性:
- 1.支持韩语及粤语
+1. 支持韩语及粤语
- 2.更好的文本前端
+2. 更好的文本前端
- 3.底模由2k小时扩展至5k小时
+3. 底模由2k小时扩展至5k小时
- 4.对低音质参考音频(尤其是来源于网络的高频严重缺失、听着很闷的音频)合成出来音质更好
+4. 对低音质参考音频(尤其是来源于网络的高频严重缺失、听着很闷的音频)合成出来音质更好
- 详见[wiki](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90v2%E2%80%90features-(%E6%96%B0%E7%89%B9%E6%80%A7))
+ 详见[wiki](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90v2%E2%80%90features-(%E6%96%B0%E7%89%B9%E6%80%A7))
从v1环境迁移至v2
- 1.需要pip安装requirements.txt更新环境
+1. 需要pip安装requirements.txt更新环境
- 2.需要克隆github上的最新代码
+2. 需要克隆github上的最新代码
- 3.需要从[huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main/gsv-v2final-pretrained) 下载预训练模型文件放到GPT_SoVITS\pretrained_models\gsv-v2final-pretrained下
+3. 需要从[huggingface](https://huggingface.co/lj1995/GPT-SoVITS/tree/main/gsv-v2final-pretrained) 下载预训练模型文件放到GPT_SoVITS\pretrained_models\gsv-v2final-pretrained下
- 中文额外需要下载[G2PWModel_1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip)(下载G2PW模型,解压并重命名为`G2PWModel`,将其放到`GPT_SoVITS\text`目录下
+ 中文额外需要下载[G2PWModel_1.1.zip](https://paddlespeech.bj.bcebos.com/Parakeet/released_models/g2p/G2PWModel_1.1.zip)(下载G2PW模型,解压并重命名为`G2PWModel`,将其放到`GPT_SoVITS/text`目录下)
## 待办事项清单
-- [ ] **高优先级:**
+- [x] **高优先级:**
- [x] 日语和英语的本地化。
- [x] 用户指南。
- [x] 日语和英语数据集微调训练。
- [ ] **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。
+ - [x] 零样本声音转换(5 秒)/ 少样本声音转换(1 分钟)。
+ - [x] TTS 语速控制。
+ - [ ] ~~增强的 TTS 情感控制。~~
- [ ] 尝试将 SoVITS 令牌输入更改为词汇的概率分布。
- - [ ] 改进英语和日语文本前端。
+ - [x] 改进英语和日语文本前端。
- [ ] 开发体积小和更大的 TTS 模型。
- [x] Colab 脚本。
- [ ] 扩展训练数据集(从 2k 小时到 10k 小时)。
- - [ ] 更好的 sovits 基础模型(增强的音频质量)。
+ - [x] 更好的 sovits 基础模型(增强的音频质量)。
- [ ] 模型混合。
## (附加)命令行运行方式
@@ -350,6 +336,8 @@ python ./tools/asr/fasterwhisper_asr.py -i -o