heimoshuiyu/ultimatevocalremovergui
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add files via upload

Browse Source
This commit is contained in:
Anjok07
2022-12-18 21:19:16 -06:00
committed by GitHub
parent a58c26520d
commit d0eb77dcf3
1 changed files with 155 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

295
README.md
View File

@@ -1,140 +1,155 @@
# Ultimate Vocal Remover GUI v5.4.0 # Ultimate Vocal Remover GUI v5.5.0
<img src="https://raw.githubusercontent.com/Anjok07/ultimatevocalremovergui/master/img/UVR_v54.png?raw=true" /> <img src="https://raw.githubusercontent.com/Anjok07/ultimatevocalremovergui/master/img/UVR_v54.png?raw=true" />
[![Release](https://img.shields.io/github/release/anjok07/ultimatevocalremovergui.svg)](https://github.com/anjok07/ultimatevocalremovergui/releases/latest) [![Release](https://img.shields.io/github/release/anjok07/ultimatevocalremovergui.svg)](https://github.com/anjok07/ultimatevocalremovergui/releases/latest)
[![Downloads](https://img.shields.io/github/downloads/anjok07/ultimatevocalremovergui/total.svg)](https://github.com/anjok07/ultimatevocalremovergui/releases) [![Downloads](https://img.shields.io/github/downloads/anjok07/ultimatevocalremovergui/total.svg)](https://github.com/anjok07/ultimatevocalremovergui/releases)
English | [简体中文](README_CN.md) ## About
## About This application uses state-of-the-art source separation models to remove vocals from audio files. UVR's core developers trained all of the models provided in this package (except for the Demucs v3 and v4 4-stem models).
This application uses state-of-the-art source separation models to remove vocals from audio files. UVR's core developers trained all of the models provided in this package (except for the Demucs v3 4-stem models). - **Core Developers**
- [Anjok07](https://github.com/anjok07)
- **Core Developers** - [aufr33](https://github.com/aufr33)
- [Anjok07](https://github.com/anjok07)
- [aufr33](https://github.com/aufr33) - **Support the Project**
- [Donate](https://www.buymeacoffee.com/uvr5)
- **Support the Project**
- [Donate](https://www.buymeacoffee.com/uvr5) ## Installation
## Installation ### Windows Installation
### Windows Installation This installation bundle contains the UVR interface, Python, PyTorch, and other dependencies needed to run the application effectively. No prerequisites are required.
This installation bundle contains the UVR interface, Python, PyTorch, and other dependencies needed to run the application effectively. No prerequisites are required. - Please Note:
- This installer is intended for those running Windows 10 or higher.
- Please Note: - Application functionality for systems running Windows 7 or lower is not guaranteed.
- This installer is intended for those running Windows 10 or higher. - Application functionality for Intel Pentium & Celeron CPUs systems is not guaranteed.
- Application functionality for systems running Windows 7 or lower is not guaranteed.
- Application functionality for Intel Pentium & Celeron CPUs systems is not guaranteed. - Download the UVR installer via the link below:
- [Main Download Link]()
- Download the UVR installer via the link below: - [Main Download Link mirror]()
- [Main Download Link](https://uvr.uvr.workers.dev/UVR_v5.4.0_setup.exe) - Update Package instructions for those who have UVR already installed:
- [Main Download Link mirror](https://www.mediafire.com/file/nrakuh8t8p993y8/UVR_v5.4.0_setup.exe) - Please download the patch straight through the application.
- Update Package instructions for those who have UVR already installed: - **Optional**
- [Update Package](https://github.com/Anjok07/ultimatevocalremovergui/releases/download/v5.4.0/UVR_v5.4_Update_Package.exe) - Additional models and application patches can be downloaded via the "Settings" menu within the application.
- **Optional**
- Additional models and application patches can be downloaded via the "Settings" menu within the application. - **Please Note:** Please install UVR to the main C:\ drive if you use the Windows installer. Installing UVR to a secondary drive will cause application instability.
- **Please Note:** Please install UVR to the main C:\ drive if you use the Windows installer. Installing UVR to a secondary drive will cause application instability. ### Other Platforms
### Other Platforms - MacOS: A fully compatible version for Mac is currently in the works and will be released soon.
- Linux: Linux installs will need to be done manually. See the Manual install section for more information.
This application does not currently run efficiently on Mac & Linux platforms yet. However, you can experiment with it by performing a manual install (see the **Manual Developer Installation** section below for more information). Some features may not be available on non-Windows platforms. An all-in-one version for MacOS will be coming soon.
### Other Application Notes
## Application Manual
- Nvidia GPUs with at least 8GBs of V-RAM are recommended.
**General Options** - This application is only compatible with 64-bit platforms.
- This application relies on Sox - Sound Exchange for Noise Reduction.
<img src="https://github.com/Anjok07/ultimatevocalremovergui/blob/master/img/gen_opt.png?raw=true" /> - This application relies on FFmpeg to process non-wav audio files.
- The application will automatically remember your settings when closed.
**VR Architecture Options** - Conversion times will significantly depend on your hardware.
- These models are computationally intensive. Please proceed with caution and pay attention to your PC to ensure it doesn't overheat. ***We are not responsible for any hardware damage.***
<img src="https://github.com/Anjok07/ultimatevocalremovergui/blob/master/img/vr_opt.png?raw=true" />
## Change Log
**MDX-Net Options**
### Patch Version:
<img src="https://github.com/Anjok07/ultimatevocalremovergui/blob/master/img/mdx_opt.png?raw=true" />
- UVR_Patch_12_18_22_6_41
**Demucs v3 Options**
### Fixes & Changes:
<img src="https://github.com/Anjok07/ultimatevocalremovergui/blob/master/img/demucs_opt.png?raw=true" />
- The progress bar is now fully synced up with every process in the application.
**Ensemble Options** - Drag-n-drop feature should now work every time.
- Users can now drop massive amounts of files and directories as inputs, and the application will add them to the conversion list.
<img src="https://github.com/Anjok07/ultimatevocalremovergui/blob/master/img/ense_opt.png?raw=true" /> - Various bug fixes for the Download Center.
- Various design changes.
**User Ensemble**
### Performance:
<img src="https://github.com/Anjok07/ultimatevocalremovergui/blob/master/img/user_ens_opt.png?raw=true" />
- Model load times are faster.
### Other Application Notes - Importing/exporting audio files is faster.
- Nvidia GPUs with at least 8GBs of V-RAM are recommended. ### New Options:
- This application is only compatible with 64-bit platforms.
- This application relies on Sox - Sound Exchange for Noise Reduction. - "Select Saved Settings" option - Allows the user to save the current settings of the whole application or reset them to the default.
- This application relies on FFmpeg to process non-wav audio files. - "Right-click" menu - Allows for quick access to important options.
- The application will automatically remember your settings when closed. - "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.
- Conversion times will significantly depend on your hardware. - Secondary Model Mode - This option is an expanded version of the "Demucs Model" option that was only available to MDX-Net. Except now, this option is available in all three AI Networks and stems. Any model can now be Secondary, and the user can choose the amount of influence the Secondary model has, unlike before.
- These models are computationally intensive. Please proceed with caution and pay attention to your PC to ensure it doesn't overheat. ***We are not responsible for any hardware damage.*** - Robust caching for ensemble mode, allowing for much faster processing times.
- You can now drag and drop as many files/folders as inputs. The application willautomatically go through each selected directory for audio files.
## Change Log - Clicking the "Input" field will pop-up a new window that allows the user to go through all of the selected audio inputs and remove some, if desired.
- "Sample Mode" option - Allows the user to process only part of a track to sample settings or a model without running a full conversion.
- **v4 vs. v5** - The number in the parentheses is the current number of seconds the generated sample will be.
- The v5 models significantly outperform the v4 models. - You can choose the number of seconds to extract from the track in the "Additional Settings" menu.
- The extraction's aggressiveness can be adjusted using the "Aggression Setting." The default value of 10 is optimal for most tracks.
- All v2 and v4 models have been removed. ### VR Architecture:
- Ensemble Mode added - This allows the user to get the most robust result from each model.
- Stacked models have been entirely removed. - Support for the latest VR architecture
The new aggression setting and model ensembling have replaced the stacked model feature. - Crop Size and Batch Size are specifically for models using the latest architecture only.
- The NFFT, HOP_SIZE, and SR values are now set internally. - Ability to toggle "High-End Processing."
- The MDX-NET AI engine and models have been added.
- This is a brand new feature added to the UVR GUI. ### MDX-NET:
- 4 MDX-Net models are included in this package.
- The MDX-Net models provided were trained by the core UVR developers - "Denoise Output" option - When enabled, this option results in cleaner results, but the processing time will be longer. This option has replaced Noise Reduction.
- This network is less resource-intensive but incredibly powerful. - "Spectral Inversion" option - This option uses inversion techniques for a cleaner secondary stem result. This option may slow down the audio export process.
- MDX-Net is a Hybrid Waveform/Spectrogram network. - Secondary stem now has the same frequency cut-off as the main stem.
- The Demucs v3 AI engine and models have been added.
- The ability to separate all 4 stems through Demucs v3. ### Demucs:
## Troubleshooting - Demucs v4 models are now supported, including the 6 stem models.
- Ability to combine remaining stems instead of inverting selected stems with the
### Common Issues mixture only when a user selects 2 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.
- 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". ### Ensemble Mode:
### Issue Reporting - Ensemble Mode has been extended to include the following:
- "Averaging" is a new algorithm that averages the final results.
Please be as detailed as possible when posting a new issue. - Unlimited models in the ensemble.
- Ability to save different ensembles.
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. - Ability to ensemble outputs for all individual stem types.
- Ability to choose unique ensemble algorithms.
## Manual Installation (For Developers) - Ability to ensemble all 4 Demucs stems at once.
**PLEASE NOTE:** Manual installs are **not** possible at this time! I am rewriting UVR's entire codebase for better readability, optimized application performance, enhanced features, and streamlined cross-platform compatibility. The new code will be released **before** the end of 2022. ## Troubleshooting
## License ### Common Issues
The **Ultimate Vocal Remover GUI** code is [MIT-licensed](LICENSE). - 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".
- **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.
### Issue Reporting
## Credits
Please be as detailed as possible when posting a new issue.
- [DilanBoskan](https://github.com/DilanBoskan) - Your contributions at the start of this project were essential to the success of UVR. Thank you!
- [Bas Curtiz](https://www.youtube.com/user/bascurtiz) - Designed the official UVR logo, icon, banner, and splash screen. 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.
- [tsurumeso](https://github.com/tsurumeso) - Developed the original VR Architecture code.
- [Kuielab & Woosung Choi](https://github.com/kuielab) - Developed the original MDX-Net AI code. ## Manual Installation (For Developers)
- [Adefossez & Demucs](https://github.com/facebookresearch/demucs) - Developed the original Demucs AI code.
- [KimberleyJSN](https://github.com/KimberleyJensen) - Advised and aided the implementation of the training scripts for MDX-Net and Demucs. Thank you! **PLEASE NOTE:** Manual installs are **not** possible at this time! The new manual install instructions will be updated before the end of the year.
- [Hv](https://github.com/NaJeongMo/Colab-for-MDX_B) - Helped implement chunks into the MDX-Net AI code. Thank you!
## License
## Contributing
The **Ultimate Vocal Remover GUI** code is [MIT-licensed](LICENSE).
- 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. - **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.
- We only maintain the development and support for the **Ultimate Vocal Remover GUI** and the models provided.
## Credits
## References
- [1] Takahashi et al., "Multi-scale Multi-band DenseNets for Audio Source Separation", https://arxiv.org/pdf/1706.09588.pdf - [DilanBoskan](https://github.com/DilanBoskan) - Your contributions at the start of this project were essential to the success of UVR. Thank you!
- [Bas Curtiz](https://www.youtube.com/user/bascurtiz) - Designed the official UVR logo, icon, banner, and splash screen.
- [tsurumeso](https://github.com/tsurumeso) - Developed the original VR Architecture code.
- [Kuielab & Woosung Choi](https://github.com/kuielab) - Developed the original MDX-Net AI code.
- [Adefossez & Demucs](https://github.com/facebookresearch/demucs) - Developed the original Demucs AI code.
- [KimberleyJSN](https://github.com/KimberleyJensen) - Advised and aided the implementation of the training scripts for MDX-Net and Demucs. Thank you!
- [Hv](https://github.com/NaJeongMo/Colab-for-MDX_B) - 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