About

This application uses state-of-the-art source separation models to remove vocals from audio files.（这个程序使用了最先进的AI模型，能从音频文件中移除人声）

UVR's core developers trained all of the models provided in this package (except for the Demucs v3 and v4 4-stem models).（URV核心开发者训练了这个软件包中所有的模型，除了Demucs v3 和 v4 4-stem）

• Core Developers（核心开发人员）

  • Anjok07
  • aufr33

• Support the Project（捐赠入口）

  • Donate

Installation

These bundles contain the UVR interface, Python, PyTorch, and other dependencies needed to run the application effectively. No prerequisites are required.

该程序分支包含了UVR界面，python，PyTorch和其他必须的组件。不需要其他先决条件。

Windows Installation

• Please Note:

  • This installer is intended for those running Windows 10 or higher.（win10及以上系统才可用）
  • Application functionality for systems running Windows 7 or lower is not guaranteed.（win7及以下系统不推荐）
  • Application functionality for Intel Pentium & Celeron CPUs systems is not guaranteed.（奔腾和赛扬CPU是不支持的）
  • You must install UVR to the main C:\ drive. Installing UVR to a secondary drive will cause instability.（你必须把URV安装到C盘默认目录，安装到其他盘会导致不稳定）

• Download the UVR installer for Windows via the link below:

  • Main Download Link （亲测不可用，需要梯子）
  • Main Download Link mirror （可以直接下载，大小1.57GB，速度300K左右）

• Update Package instructions for those who have UVR already installed:

  • If you already have UVR installed you can install this package over it or download it straight from the application.（如果你安装的有旧版本，直接覆盖安装即可，没装过就直接安装）

Manual Windows Installation

• Download and extract the repository here （下载和解压仓库）
• https://github.com/Anjok07/ultimatevocalremovergui/archive/refs/heads/master.zip
Download and install Python 

 （安装Python 3.9.8 官方推荐的版本https://www.python.org/ftp/python/3.9.8/python-3.9.8-amd64.exe

）
• Make sure to check "Add python.exe to PATH" during the install（安装python时确保"Add python.exe to PATH"前打勾）
• Run the following commands from the extracted repo directory:（在解压后的仓库目录里cmd运行以下命令）

python.exe -m pip install -r requirements.txt

If you have a compatible Nvidia GPU, run the following command:(如果你有兼容的N卡GPU，还要运行以下命令)

python.exe -m pip install --upgrade torch --extra-index-url https://download.pytorch.org/whl/cu117

If you do not have FFmpeg or Rubber Band installed and want to avoid going through the process of installing them the long way, follow the instructions below.（还得安装FFmpeg和Rubber Band组件）

FFmpeg Installation

• Download the precompiled build here
• From the archive, extract the following file to the UVR application directory:
  • ffmpeg-5.1.2-essentials_build/bin/ffmpeg.exe

Rubber Band Installation

In order to use the Time Stretch or Change Pitch tool, you'll need Rubber Band.

• Download the precompiled build here
• From the archive, extract the following files to the UVR application directory:
  • rubberband-3.1.2-gpl-executable-windows/rubberband.exe
  • rubberband-3.1.2-gpl-executable-windows/sndfile.dll

MacOS Installation

• Please Note:

  • This bundle is intended for those running macOS Catalina and above.
  • Application functionality for systems running macOS Mojave or lower is not guaranteed.
  • Application functionality for older or budget Mac systems is not guaranteed.
  • Once everything is installed, the application may take up to 5-10 minutes to start for the first time (depending on your Macbook).

• Download the UVR dmg for MacOS via one of the links below:

  • Mac M1 (arm64) users:

    • Main Download Link
    • Main Download Link mirror

  • Mac Intel (x86_64) users:

    • Main Download Link
    • Main Download Link mirror

Linux Installation

Other Application Notes

• Nvidia RTX 1060 6GB is the minimum requirement for GPU conversions.（N卡1060 6G版本是最低显卡要求）
• Nvidia GPUs with at least 8GBs of V-RAM are recommended.
• AMD Radeon GPUs are not supported at this time.(A卡目前不支持的哦)
• This application is only compatible with 64-bit platforms.（只兼容64位系统且只提供64位安装包）
• This application relies on the Rubber Band library for the Time-Stretch and Pitch-Shift options.
• This application relies on FFmpeg to process non-wav audio files.
• The application will automatically remember your settings when closed.（关闭程序会记住你刚使用的设定）
• Conversion times will significantly depend on your hardware.（分离音频用的时间取决于你的硬件）
• These models are computationally intensive.（程序使用的分离模型完全依赖于硬件的计算能力主要是GPU）

Change Log

Most Recent Changes:（5.5.1改进了啥）

• Fixed Download Center model list issue.（修复了下载中心模型列表功能）
• Fixed audio clip in ensemble mode.（整体分离模型修复）
• Fixed output model name issue in ensemble mode.（修复了输出文件名称问题）
• Added "Batch Mode" for MDX-Net to increase performance.（加入了批量处理音频文件的功能）
  • Batch Mode is more memory efficient.（更有效）
  • Batch Mode produces the best output, regardless of batch size.
• Added Batch Mode for VR Architecture.
• Added Mixer Mode for Demucs.
  • This option may improve separation for some 4-stem models.

Fixes & Changes going from UVR v5.4 to v5.5:

• The progress bar is now fully synced up with every process in the application.
• Drag-n-drop feature should now work every time.
• Users can now drop large batches of files and directories as inputs. When directories are dropped, the application will search for any file with an audio extension and add it to the list of inputs.
• Fixed low-resolution icon.
• Added the ability to download models manually if the application can't connect to the internet.
• Various bug fixes for the Download Center.
• Various design changes.

Performance:

• Model load times are faster.
• Importing/exporting audio files is faster.

New Options:

• "Select Saved Settings" option - Allows the user to save the current settings of the whole application. You can also load saved settings or reset them to the default.
• "Right-click" menu - Allows for quick access to important options.
• "Help Hints" option - When enabled, users can hover over options to see pop-up text that describes that option. The right-clicking option also allows copying the "Help Hint" text.
• Secondary Model Mode - This option is an expanded version of the "Demucs Model" option only available to MDX-Net. Except now, this option is available in all three AI Networks and for any stem. Any model can now be Secondary, and the user can choose the amount of influence it has on the final result.
• Robust caching for ensemble mode, allowing for much faster processing times.
• Clicking the "Input" field will pop up a new window that allows the user to go through all of the selected audio inputs. Within this menu, users can:
  • Remove inputs.
  • Verify inputs.
  • Create samples of selected inputs.
• "Sample Mode" option - Allows the user to process only part of a track to sample settings or a model without running a complete conversion.
  • The number in the parentheses is the current number of seconds the generated sample will be.
  • You can choose the number of seconds to extract from the track in the "Additional Settings" menu.

VR Architecture:

• Ability to toggle "High-End Processing."
• Support for the latest VR architecture
  • Crop Size and Batch Size are specifically for models using the latest architecture only.

MDX-NET:

• "Denoise Output" option results in cleaner results, but the processing time will be longer. This option has replaced Noise Reduction.
• "Spectral Inversion" option uses spectral inversion techniques for a cleaner secondary stem result. This option may slow down the audio export process.
• Secondary stem now has the same frequency cut-off as the main stem.

Demucs:

• Demucs v4 models are now supported, including the 6-stem model.
• Combining remaining stems instead of inverting selected stem with the mixture only when a user does not select "All Stems."
• A "Pre-process" model that allows the user to run an inference through a robust vocal or instrumental model and separate the remaining stems from its generated instrumental mix. This option can significantly reduce vocal bleed in other Demucs-generated non-vocal stems.
  • The Pre-process model is intended for Demucs separations for all stems except vocals and instrumentals.

Ensemble Mode:

• Ensemble Mode has been extended to include the following:
  • "Averaging" is a new algorithm that averages the final results.
  • Unlimited models in the ensemble.
  • Ability to save different ensembles.
  • Ability to ensemble outputs for all individual stem types.
  • Ability to choose unique ensemble algorithms.
  • Ability to ensemble all 4 Demucs stems at once.

Troubleshooting

Common Issues

• If FFmpeg is not installed, the application will throw an error if the user attempts to convert a non-WAV file.
• Memory allocation errors can usually be resolved by lowering the "Chunk Size".

Issue Reporting

Please be as detailed as possible when posting a new issue.

If possible, click the "Settings Button" to the left of the "Start Processing" button and click the "Error Log" button for detailed error information that can be provided to us.

License

The Ultimate Vocal Remover GUI code is MIT-licensed.

• Please Note: For all third-party application developers who wish to use our models, please honor the MIT license by providing credit to UVR and its developers.

Credits

• DilanBoskan - Your contributions at the start of this project were essential to the success of UVR. Thank you!
• Bas Curtiz - Designed the official UVR logo, icon, banner, and splash screen.
• tsurumeso - Developed the original VR Architecture code.
• Kuielab & Woosung Choi - Developed the original MDX-Net AI code.
• Adefossez & Demucs - Developed the original Demucs AI code.
• KimberleyJSN - Advised and aided the implementation of the training scripts for MDX-Net and Demucs. Thank you!
• Hv - Helped implement chunks into the MDX-Net AI code. Thank you!

Contributing

• For anyone interested in the ongoing development of Ultimate Vocal Remover GUI, please send us a pull request, and we will review it.
• This project is 100% open-source and free for anyone to use and modify as they wish.
• We only maintain the development and support for the Ultimate Vocal Remover GUI and the models provided.

References

• [1] Takahashi et al., "Multi-scale Multi-band DenseNets for Audio Source Separation", https://arxiv.org/pdf/1706.09588.pdf