blackteay/GPT-SoVITS
1
0
Fork 0
mirror of https://github.com/RVC-Boss/GPT-SoVITS.git synced 2026-04-29 21:00:42 +08:00
Code Issues Packages Projects Releases Wiki Activity
1,044 Commits 3 Branches 4 Tags
Commit Graph

45 Commits

Author SHA1 Message Date
changhaowuwu
63adee93a6
Merge 8b195a5adb362c35c65ca4ab093543a1168fb221 into ea2d2a81667239d37615697e8f0056e35bab2db6 2026-04-21 01:39:28 +00:00
huang yutong
14191901cd
fix: 修复多个模块中的独立 bug (#2755) 
1. 修复 sync_buffer 中除以函数对象而非调用结果（distrib.py）
   - `buffer.data /= world_size` 中 world_size 是函数，缺少 ()，
     导致 TypeError 使分布式训练 buffer 同步失败

2. 修复 istft 函数缺少 return 语句（spec_utils.py）
   - 函数计算了结果但未返回，调用者始终得到 None

3. 修复 cut0 返回字面量 "/n" 而非换行符 "\n"（text_segmentation_method.py）
   - 导致后续 text.split("\n") 无法正确切分，字面 /n 被当作文本内容

4. 修复粤语 ASR 的 vad/punc model_revision 被无条件覆盖（funasr_asr.py）
   - 粤语分支将 vad_model_revision 设为空（因不使用 VAD/标点模型），
     但 if/else 外的赋值将其覆盖为 "v2.0.4"，传入错误的 revision 参数

Made-with: Cursor
 2026-04-18 17:10:56 +08:00
changhaowuwu
8b195a5adb security: replace eval() with safe boolean parsing 
Replace all uses of eval() on environment variables and command-line
arguments with safe string comparison. eval() allows arbitrary code
execution when given untrusted input, making it a security risk.

The fix uses .lower() in ("true", "1", "yes") which produces
identical behavior for all valid boolean inputs while preventing
code injection. This pattern is already used in config.py.

Affected files (10 call sites):
- GPT_SoVITS/inference_webui.py (is_share, is_half)
- GPT_SoVITS/inference_webui_fast.py (is_share, is_half)
- GPT_SoVITS/prepare_datasets/1-get-text.py (is_half)
- GPT_SoVITS/prepare_datasets/2-get-hubert-wav32k.py (is_half)
- GPT_SoVITS/prepare_datasets/2-get-sv.py (is_half)
- GPT_SoVITS/prepare_datasets/3-get-semantic.py (is_half)
- tools/uvr5/webui.py (is_half, is_share)
- tools/subfix_webui.py (is_share)
 2026-02-25 22:08:01 +01:00
XXXXRT666
6fdc67ca83
Fix bugs in install.sh, reduce log noise, and improve error reporting (#2464) 
* Update Install.sh

* Format Code

* Delete dev null

* Update README, Support Dark Mode in CSS/JS
 2025-06-17 15:21:36 +08:00
RVC-Boss
1934fc1e1b
修复uvr5和onnx去混响模型ffmpeg编码mp3和m4a原路径带空格会有bug的问题 
修复uvr5和onnx去混响模型ffmpeg编码mp3和m4a原路径带空格会有bug的问题
 2025-05-29 11:14:01 +08:00
XXXXRT666
d5e479dad6
Introduce Docker and Windows CI Workflow, Pre-commit Formatting, and Language Resource Auto-Download (#2351) 
* Docker Auto-Build Workflow

* Rename

* Update

* Fix Bugs

* Disable Progress Bar When workflows triggered

* Fix Wget

* Fix Bugs

* Fix Bugs

* Update Wget

* Update Workflows

* Accelerate Docker Image Building

* Fix Install.sh

* Add Skip-Check For Action Runner

* Fix Dockerfile

* .

* .

* .

* .

* Delete File in Runner

* Add Sort

* Delete More Files

* Delete More

* .

* .

* .

* Add Pre-Commit Hook
Update Docker

* Add Code Spell Check

* [pre-commit.ci] trigger

* [pre-commit.ci] trigger

* [pre-commit.ci] trigger

* Fix Bugs

* .

* Disable Progress Bar and Logs while using GitHub Actions

* .

* .

* Fix Bugs

* update conda

* fix bugs

* Fix Bugs

* fix bugs

* .

* .

* Quiet Installation

* fix bugs

* .

* fix bug

* .

* Fix pre-commit.ci and Docker

* fix bugs

* .

* Update Docker & Pre-Commit

* fix  bugs

* Update Req

* Update Req

* Update OpenCC

* update precommit

* .

* Update .pre-commit-config.yaml

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update Docs and fix bugs

* Fix \

* Fix MacOS

* .

* test

* .

* Add Tag Alias

* .

* fix bugs

* fix bugs

* make image smaller

* update pre-commit config

* .

* .

* fix bugs

* use miniconda

* Fix Wrong Path

* .

* debug

* debug

* revert

* Fix Bugs

* Update Docs, Add Dict Auto Download in install.sh

* update docker_build

* Update Docs for Install.sh

* update docker docs about architecture

* Add Xcode-Commandline-Tool Installation

* Update Docs

1. Add Missing VC17
2. Modufied the Order of FFmpeg Installation and Requirements Installation
3. Remove Duplicate FFmpeg

* Fix Wrong Cuda Version

* Update TESTED ENV

* Add PYTHONNOUSERSITE(-s)

* Fix Wrapper

* Update install.sh For Robustness

* Ignore .git

* Preload CUDNN For Ctranslate2

* Remove Gradio Warnings

* Update Colab

* Fix OpenCC Problems

* Update Win DLL Strategy

* Fix Onnxruntime-gpu NVRTC Error

* Fix Path Problems

* Add Windows Packages Workflow

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* .

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* WIP

* Fix Path

* Fix Path

* Enable Logging

* Set 7-Zip compression level to maximum (-mx=9)

* Use Multithread in ONNX Session

* Fix Tag Bugs

* Add Time

* Add Time

* Add Time

* Compress More

* Copy DLL to Solve VC Runtime DLL Missing Issues

* Expose FFmpeg Errors, Copy Only Part of Visual C++ Runtime

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* Update build_windows_packages.ps1

* WIP

* WIP

* WIP

* Update build_windows_packages.ps1

* Update install.sh

* Update build_windows_packages.ps1

* Update docker-publish.yaml

* Update install.sh

* Update Dockerfile

* Update docker_build.sh

* Update miniconda_install.sh

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update README.md

* Update Colab-WebUI.ipynb

* Update Colab-Inference.ipynb

* Update docker-compose.yaml

* 更新 build_windows_packages.ps1

* Update install.sh

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2025-05-26 10:45:14 +08:00
XXXXRT666
9202c74761
Update Gradio Reqs (#2311) 
* Update Librosa version

* Update Gradio Quiet Settings
 2025-04-22 20:28:04 +08:00
XXXXRT666
53cac93589
Refactor: Format Code with Ruff and Update Deprecated G2PW Link (#2255) 
* ruff check --fix

* ruff format --line-length 120 --target-version py39

* Change the link for G2PW Model

* update pytorch version and colab
 2025-04-07 16:42:47 +08:00
starylan
e35ade8f60 拆分i18n 2025-02-28 01:41:04 +08:00
Sucial
e061e9d38e
Support for mel_band_roformer (#2078) 
* support for mel_band_roformer

* Remove unnecessary audio channel judgments

* remove context manager and fix path

* Update webui.py

* Update README.md
 2025-02-23 20:28:53 +08:00
XXXXRT666
7dac47ca95
chores (#1528) 
* chores

* ...

* Add files via upload

* ...

* remove gradio warnings

* Update inference_webui.py

Fix inference_cli issue
 2024-08-23 17:47:27 +08:00
RVC-Boss
0e02585580
Update gradio 2024-08-20 23:47:48 +08:00
XXXXRT666
ea56b814bd
Chores (#1422) 
Make Gradio Great Again
附带vs2017下载链接
增加了各种数据集检查,若缺失会弹出warning
修复了warning乱弹的bug
修复了参考音频混合只能上传一条的bug
修复了下载G2PW Model出现import错误的bug
修复了Windows训练无N卡在预处理阶段的报错
 2024-08-13 16:31:12 +08:00
RVC-Boss
9498fc775b
bsroformer support fp16 inference 
bsroformer support fp16 inference
 2024-08-01 21:28:06 +08:00
RVC-Boss
e62e965323
bsroformer support fp16 inference 
bsroformer support fp16 inference
 2024-08-01 21:26:59 +08:00
KamioRinn
7670bc77c3
Simplify BSR (#1356) 2024-07-30 10:32:37 +08:00
KamioRinn
8abc0342d7
为UVR5模块添加Bs_Roformer模型 (#1306) 
* Add Bs_Roformer

* Compatible with default model name

* Add progress bar
 2024-07-27 16:37:28 +08:00
蓝梦实
7e7073b45a
Update i18n to the Latest (#1344) 
* 拆分UVR5长注释

* 更新JSON文件

* Update JSON
 2024-07-24 14:39:03 +08:00
XXXXRT666
0a3a1e4505
Clean Path (#1299) 
* clean path

* clean path
 2024-07-13 19:17:46 +08:00
RVC-Boss
501a74ae96
Add files via upload 2024-06-10 16:14:15 +08:00
SapphireLab
8582131bd8
fix reformat cmd (#917) 
Co-authored-by: starylan <starylan@outlook.com>
 2024-04-03 17:42:42 +08:00
jiaqianjing
36d2b57e9d remove useless code 2024-03-10 00:03:38 +08:00
ShiroDoMain
35e673d801 fix MDX-Net output path 2024-02-27 15:19:47 +08:00
RVC-Boss
14a285109a
Update webui.py 2024-02-07 11:52:52 +08:00
SapphireLab
def1f4e3da 适配更高版本的 librosa 2024-02-06 03:12:24 +08:00
KamioRinn
147218c529 Fix uvr5 2024-02-05 01:29:16 +08:00
RVC-Boss
e3d792fb56
修复uvr5识别格式失败报错问题。除非列举不能识别的bad case，否则禁止改动此文件。 
修复uvr5识别格式失败报错问题。除非列举不能识别的bad case，否则禁止改动此文件。
 2024-02-04 15:09:07 +08:00
RVC-Boss
0945de3b7f
Update webui.py 2024-01-28 21:52:07 +08:00
RVC-Boss
2c72a8fcd4
Update webui.py 2024-01-28 21:40:52 +08:00
RVC-Boss
329d99fb51
Add files via upload 2024-01-28 21:39:32 +08:00
KamioRinn
f7130944c0 fix uvr5 hp3 output 2024-01-27 06:00:48 +08:00
RVC-Boss
2d1ddeca42
Add files via upload 2024-01-26 16:34:11 +08:00
RVC-Boss
813cf96e50
Add files via upload 2024-01-26 11:49:33 +08:00
Rice Cake
40603d00c2
Add files via upload 2024-01-22 20:25:13 +08:00
RVC-Boss
ca5b67002b
Merge pull request #95 from KakaruHayate/patch-1 
使用librosa加载音频避免ffmpeg.probe读取metadata的错误
 2024-01-22 18:39:06 +08:00
RVC-Boss
2f3ab46bdf
Add files via upload 2024-01-21 23:02:55 +08:00
KakaruHayate
240e0e289b
使用librosa加载音频避免ffmpeg.probe读取metadata的错误 
如题，有用户称在读取音频的metadata时出现问题，这可能是ffprobe造成的。部分站点在存在写入不合规metadata的情况（如一些直播站点将直播间信息写入metadata，其中包含emoji等乱七八糟信息），这在ffmpeg.probe时将会出现问题。
考虑到ffmpeg兼容性和性能比librosa更好，可能在导入前对metadata合规性处理会更好？
但是看到后面注释部分很多地方还是使用librosa实现，所以暂且认为还不用考虑兼容性问题。
 2024-01-20 12:09:21 +08:00
RVC-Boss
a665a5314d
Merge pull request #7 from Tps-F/instead_init 
remove full-width replace init to gitignore
 2024-01-20 11:26:10 +08:00
RVC-Boss
90f940ed91
Delete tools/uvr5/uvr5_weights/onnx_dereverb_By_FoxJoy/init 2024-01-17 18:42:25 +08:00
RVC-Boss
affaf181aa
Delete tools/uvr5/init 2024-01-17 18:41:38 +08:00
Blaise
9031ac9a92 change i18n folder 2024-01-16 17:04:43 +01:00
Ftps
b1a60801e6 remove full-width replace init to gitignore 2024-01-17 00:57:07 +09:00
RVC-Boss
0a97c710f0
Create init 2024-01-16 17:34:19 +08:00
RVC-Boss
6b7a98038f
Add files via upload 2024-01-16 17:33:36 +08:00
RVC-Boss
7425d0f780
Create init 2024-01-16 17:31:35 +08:00