diff --git a/.github/build_windows_packages.ps1 b/.github/build_windows_packages.ps1
index 2e4acb2a..75918d35 100644
--- a/.github/build_windows_packages.ps1
+++ b/.github/build_windows_packages.ps1
@@ -162,7 +162,7 @@ Copy-Item -Path $curr -Destination $pkgName -Recurse
$7zPath = "$pkgName.7z"
$start = Get-Date
Write-Host "Compress Starting at $start"
-& "C:\Program Files\7-Zip\7z.exe" a -t7z "$7zPath" "$pkgName" -m0=lzma2 -mx=9 -md=1g -ms=1g -mmc=500 -mfb=273 -mlc=0 -mlp=4 -mpb=4 -mc=8g -mmt=on -bsp1
+& "C:\Program Files\7-Zip\7z.exe" a -t7z "$7zPath" "$pkgName" -m0=lzma2 -mx=9 -mmt=on -bsp1
$end = Get-Date
Write-Host "Elapsed time: $($end - $start)"
Get-ChildItem .
diff --git a/GPT_SoVITS/inference_webui.py b/GPT_SoVITS/inference_webui.py
index ce6cf9de..f9fa6a70 100644
--- a/GPT_SoVITS/inference_webui.py
+++ b/GPT_SoVITS/inference_webui.py
@@ -1333,5 +1333,6 @@ if __name__ == "__main__":
inbrowser=True,
share=is_share,
server_port=infer_ttswebui,
+ show_api=False,
# quiet=True,
)
diff --git a/GPT_SoVITS/inference_webui_fast.py b/GPT_SoVITS/inference_webui_fast.py
index 470b7bbd..608297d0 100644
--- a/GPT_SoVITS/inference_webui_fast.py
+++ b/GPT_SoVITS/inference_webui_fast.py
@@ -505,5 +505,6 @@ if __name__ == "__main__":
inbrowser=True,
share=is_share,
server_port=infer_ttswebui,
+ show_api=False,
# quiet=True,
)
diff --git a/GPT_SoVITS/text/g2pw/onnx_api.py b/GPT_SoVITS/text/g2pw/onnx_api.py
index a8268107..9d153745 100644
--- a/GPT_SoVITS/text/g2pw/onnx_api.py
+++ b/GPT_SoVITS/text/g2pw/onnx_api.py
@@ -23,8 +23,9 @@ from .utils import load_config
onnxruntime.set_default_logger_severity(3)
try:
onnxruntime.preload_dlls()
-except:pass
- #traceback.print_exc()
+except:
+ pass
+ # traceback.print_exc()
warnings.filterwarnings("ignore")
model_version = "1.1"
diff --git a/README.md b/README.md
index d03514f0..7c845800 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,5 @@
+#
+
GPT-SoVITS-WebUI
@@ -7,12 +9,17 @@ A Powerful Few-shot Voice Conversion and Text-to-Speech WebUI.

-
+[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb)
+[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-Inference.ipynb)
+[](https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2)
-[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
-[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
-[](https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2)
-[](https://discord.gg/dnrgs5GHfG)
+[](https://github.com/RVC-Boss/gpt-sovits/releases)
+[](https://hub.docker.com/r/xxxxrt666/gpt-sovits)
+[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
+
+[](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e)
+[](https://rentry.co/GPT-SoVITS-guide#/)
+[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/docs/en/Changelog_EN.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)
@@ -20,7 +27,7 @@ A Powerful Few-shot Voice Conversion and Text-to-Speech WebUI.
---
-## Features:
+## Features
1. **Zero-shot TTS:** Input a 5-second vocal sample and experience instant text-to-speech conversion.
@@ -34,13 +41,13 @@ A Powerful Few-shot Voice Conversion and Text-to-Speech WebUI.
Unseen speakers few-shot fine-tuning demo:
-https://github.com/RVC-Boss/GPT-SoVITS/assets/129054828/05bee1fa-bdd8-4d85-9350-80c060ab47fb
+
-**User guide: [简体中文](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e) | [English](https://rentry.co/GPT-SoVITS-guide#/)**
+
## Installation
-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.
+For users in China, you can use [AutoDL Cloud Docker](https://www.codewithgpu.com/i/RVC-Boss/GPT-SoVITS/GPT-SoVITS-Official) to experience the full functionality online.
### Tested Environments
@@ -171,7 +178,7 @@ docker exec -it
```
-if you want to switch to V1,then
-
-```bash
-python webui.py v1
-```
-
-Or maunally switch version in WebUI
-
### Finetune
#### Path Auto-filling is now supported
@@ -253,7 +247,7 @@ Or maunally switch version in WebUI
#### Integrated Package Users
-Double-click `go-webui-v2.bat` or use `go-webui-v2.ps1` ,then open the inference webui at `1-GPT-SoVITS-TTS/1C-inference`
+Double-click `go-webui.bat` or use `go-webui.ps1` , then open the inference webui at `1-GPT-SoVITS-TTS/1C-inference`
#### Others
@@ -333,7 +327,7 @@ Use v4 from v1/v2/v3 environment:
New Features:
1. Slightly higher VRAM usage than v2, surpassing v4's performance, with v2's hardware cost and speed.
- [more details](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90features-(%E5%90%84%E7%89%88%E6%9C%AC%E7%89%B9%E6%80%A7))
+ [more details]()
2.v1/v2 and the v2Pro series share the same characteristics, while v3/v4 have similar features. For training sets with average audio quality, v1/v2/v2Pro can deliver decent results, but v3/v4 cannot. Additionally, the synthesized tone and timebre of v3/v4 lean more toward the reference audio rather than the overall training set.
@@ -373,11 +367,6 @@ Use the command line to open the WebUI for UVR5
python tools/uvr5/webui.py ""
```
-
-
This is how the audio segmentation of the dataset is done using the command line
```bash
@@ -453,5 +442,5 @@ Thankful to @Naozumi520 for providing the Cantonese training set and for the gui
## Thanks to all contributors for their efforts
-
+
diff --git a/docker_build.ps1 b/docker_build.ps1
new file mode 100644
index 00000000..c0508fa6
--- /dev/null
+++ b/docker_build.ps1
@@ -0,0 +1,73 @@
+$ErrorActionPreference = "Stop"
+
+$ScriptDir = Split-Path -Parent $MyInvocation.MyCommand.Definition
+Set-Location $ScriptDir
+
+if (-not (Get-Command "docker" -ErrorAction SilentlyContinue)) {
+ Write-Host "Docker Not Found"
+ exit 1
+}
+
+$Lite = $false
+$CudaVersion = "12.6"
+
+function Write-Help {
+ Write-Host @"
+Usage: powershell -File docker_build.ps1 [OPTIONS]
+
+Options:
+ --cuda 12.6|12.8 Specify the CUDA VERSION (REQUIRED)
+ --lite Build a Lite Image
+ -h, --help Show this help message and exit
+
+Examples:
+ powershell -File docker_build.ps1 --cuda 12.6 --lite
+"@
+}
+
+if ($args.Count -eq 0) {
+ Write-Help
+ exit 0
+}
+
+for ($i = 0; $i -lt $args.Count; $i++) {
+ switch ($args[$i]) {
+ '--cuda' {
+ $i++
+ $val = $args[$i]
+ if ($val -ne "12.6" -and $val -ne "12.8") {
+ Write-Host "Error: Invalid CUDA_VERSION: $val"
+ Write-Host "Choose From: [12.6, 12.8]"
+ exit 1
+ }
+ $CudaVersion = $val
+ }
+ '--lite' {
+ $Lite = $true
+ }
+ '-h' { Write-Help; exit 0 }
+ '--help' { Write-Help; exit 0 }
+ default {
+ Write-Host "Unknown Argument: $($args[$i])"
+ Write-Host "Use -h or --help to see available options."
+ exit 1
+ }
+ }
+}
+
+$arch = (Get-CimInstance Win32_Processor).Architecture
+$TargetPlatform = if ($arch -eq 9) { "linux/amd64" } else { "linux/arm64" }
+
+if ($Lite) {
+ $TorchBase = "lite"
+} else {
+ $TorchBase = "full"
+}
+
+docker build `
+ --build-arg CUDA_VERSION=$CudaVersion `
+ --build-arg LITE=$Lite `
+ --build-arg TARGETPLATFORM=$TargetPlatform `
+ --build-arg TORCH_BASE=$TorchBase `
+ -t "$env:USERNAME/gpt-sovits:local" `
+ .
\ No newline at end of file
diff --git a/docker_build.sh b/docker_build.sh
index 354599d2..b6a803fb 100644
--- a/docker_build.sh
+++ b/docker_build.sh
@@ -25,7 +25,7 @@ print_help() {
echo " -h, --help Show this help message and exit"
echo ""
echo "Examples:"
- echo " bash docker_build.sh --cuda 12.6 --funasr --faster-whisper"
+ echo " bash docker_build.sh --cuda 12.6"
}
# Show help if no arguments provided
diff --git a/docs/cn/Changelog_CN.md b/docs/cn/Changelog_CN.md
index 6c6dcdbe..b3d620e9 100644
--- a/docs/cn/Changelog_CN.md
+++ b/docs/cn/Changelog_CN.md
@@ -157,7 +157,7 @@
- 类型: 修复
- 提交: StaryLan
- 2024.02.07 [Commit#14a28510](https://github.com/RVC-Boss/GPT-SoVITS/commit/14a285109a521679f8846589c22da8f656a46ad8)
- - 内容: 修复 UVR5 `inf everywhere` 报错的问题 (`is_half` 传参未转换布尔类型导致恒定半精度推理, 16系显卡会 `inf`).
+ - 内容: 修复 UVR5 `inf everywhere` 报错的问题 (`is_half` 传参未转换布尔类型导致恒定半精度推理, 16 系显卡会 `inf`).
- 类型: 修复
- 提交: RVC-Boss
- 2024.02.07 [Commit#d74f888e](https://github.com/RVC-Boss/GPT-SoVITS/commit/d74f888e7ac86063bfeacef95d0e6ddafe42b3b2)
@@ -230,6 +230,7 @@
## 202403
- 2024.03.06 [PR#675](https://github.com/RVC-Boss/GPT-SoVITS/pull/675)
+
- 内容: Faster Whisper 在没有 CUDA 可用时自动使用 CPU 推理.
- 类型: 优化
- 提交: ShiroDoMain
@@ -347,7 +348,7 @@
- 2024.07.23 [Commit#9588a3c5](https://github.com/RVC-Boss/GPT-SoVITS/commit/9588a3c52d9ebdb20b3c5d74f647d12e7c1171c2), [PR#1340](https://github.com/RVC-Boss/GPT-SoVITS/pull/1340)
- 内容: 支持合成语速调节, 支持冻结随机性只调节语速, 并将其更新到`api.py` 上.
- 类型: 新功能
- - 提交: RVC-Boss, 红血球AE3803
+ - 提交: RVC-Boss, 红血球 AE3803
- 2024.07.27 [PR#1306](https://github.com/RVC-Boss/GPT-SoVITS/pull/1306), [PR#1356](https://github.com/RVC-Boss/GPT-SoVITS/pull/1356)
- 内容: 增加 BS-Roformer 人声伴奏分离模型支持.
- 类型: 新功能
@@ -409,7 +410,7 @@
- 2025.02.11 [Commit#ed207c4b](https://github.com/RVC-Boss/GPT-SoVITS/commit/ed207c4b879d5296e9be3ae5f7b876729a2c43b8)~[Commit#6e2b4918](https://github.com/RVC-Boss/GPT-SoVITS/commit/6e2b49186c5b961f0de41ea485d398dffa9787b4)
- 内容: **新增 GPT-SoVITS V3 模型, 需要 14G 显存进行微调.**
- - 类型: 新功能 (特性参阅 [Wiki](https://github.com/RVC-Boss/GPT-SoVITS/wiki/GPT%E2%80%90SoVITS%E2%80%90v3%E2%80%90features-(%E6%96%B0%E7%89%B9%E6%80%A7)))
+ - 类型: 新功能 (特性参阅 [Wiki]())
- 提交: RVC-Boss
- 2025.02.12 [PR#2032](https://github.com/RVC-Boss/GPT-SoVITS/pull/2032)
- 内容: 更新项目多语言文档.
@@ -453,7 +454,7 @@
- 类型: 文档
- 提交: StaryLan
- 2025.02.28 [PR#2122](https://github.com/RVC-Boss/GPT-SoVITS/pull/2122)
- - 内容: 对于模型无法判断的CJK短字符采用规则判断.
+ - 内容: 对于模型无法判断的 CJK 短字符采用规则判断.
- 类型: 修复
- 提交: KamioRinn
- 关联: [Issue#2116](https://github.com/RVC-Boss/GPT-SoVITS/issues/2116)
@@ -475,6 +476,7 @@
- Pydantic: [Issue#2230](https://github.com/RVC-Boss/GPT-SoVITS/issues/2230), [Issue#2239](https://github.com/RVC-Boss/GPT-SoVITS/issues/2239).
- PyTorch-Lightning: [Issue#2174](https://github.com/RVC-Boss/GPT-SoVITS/issues/2174).
- 2025.03.31 [PR#2241](https://github.com/RVC-Boss/GPT-SoVITS/pull/2241)
+
- 内容: **为 SoVITS v3 适配并行推理**.
- 类型: 新功能
- 提交: ChasonJiang
diff --git a/docs/cn/README.md b/docs/cn/README.md
index e674d9cf..21ee3567 100644
--- a/docs/cn/README.md
+++ b/docs/cn/README.md
@@ -1,18 +1,25 @@
+#
+
GPT-SoVITS-WebUI
-强大的少样本语音转换与语音合成Web用户界面.
+强大的少样本语音转换与语音合成Web用户界面.
[](https://github.com/RVC-Boss/GPT-SoVITS)

-
+[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-WebUI.ipynb)
+[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/Colab-Inference.ipynb)
+[](https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2)
-[](https://colab.research.google.com/github/RVC-Boss/GPT-SoVITS/blob/main/colab_webui.ipynb)
-[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
-[](https://huggingface.co/spaces/lj1995/GPT-SoVITS-v2)
-[](https://discord.gg/dnrgs5GHfG)
+[](https://github.com/RVC-Boss/gpt-sovits/releases)
+[](https://hub.docker.com/r/xxxxrt666/gpt-sovits)
+[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/LICENSE)
+
+[](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e)
+[](https://rentry.co/GPT-SoVITS-guide#/)
+[](https://github.com/RVC-Boss/GPT-SoVITS/blob/main/docs/cn/Changelog_CN.md)
[**English**](../../README.md) | **中文简体** | [**日本語**](../ja/README.md) | [**한국어**](../ko/README.md) | [**Türkçe**](../tr/README.md)
@@ -36,7 +43,7 @@
-**用户手册: [简体中文](https://www.yuque.com/baicaigongchang1145haoyuangong/ib3g1e) | [English](https://rentry.co/GPT-SoVITS-guide#/)**
+
## 安装
@@ -171,7 +178,7 @@ docker exec -it
```
-若想使用 V1,则
-
-```bash
-python webui.py v1
-```
-
-或者在 webUI 内动态切换
-
### 微调
#### 现已支持自动填充路径
@@ -243,13 +241,13 @@ python webui.py v1
3. 进行降噪(可选)
4. 进行 ASR
5. 校对标注
-6. 前往下一个窗口,点击训练
+6. 前往下一个窗口, 点击训练
### 打开推理 WebUI
#### 整合包用户
-双击 `go-webui.bat` 或者使用 `go-webui.ps1` ,然后在 `1-GPT-SoVITS-TTS/1C-推理` 中打开推理 webUI
+双击 `go-webui.bat` 或者使用 `go-webui.ps1` , 然后在 `1-GPT-SoVITS-TTS/1C-推理` 中打开推理 webUI
#### 其他
@@ -287,7 +285,7 @@ python webui.py
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.zip(HF)](https://huggingface.co/XXXXRT/GPT-SoVITS-Pretrained/resolve/main/G2PWModel.zip)| [G2PWModel.zip(ModelScope)](https://www.modelscope.cn/models/XXXXRT/GPT-SoVITS-Pretrained/resolve/master/G2PWModel.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.zip(HF)](https://huggingface.co/XXXXRT/GPT-SoVITS-Pretrained/resolve/main/G2PWModel.zip)| [G2PWModel.zip(ModelScope)](https://www.modelscope.cn/models/XXXXRT/GPT-SoVITS-Pretrained/resolve/master/G2PWModel.zip) (下载 G2PW 模型, 解压并重命名为`G2PWModel`, 将其放到`GPT_SoVITS/text`目录下)
## V3 更新说明
@@ -449,5 +447,5 @@ python ./tools/asr/fasterwhisper_asr.py -i -o