This colab is based on python-audio-separator (a CLI version of UVR5). This project was originally created for the AI HUB community.
- All VR Arch Models
- All MDX-NET Models
- Demucs v4 Models
- MDX23C Models
- BS-Roformer ViperX Models
- VIP Models
- Drumsep (Drum separation based on a Hybrid Demucs model)
- Batch Separation
- Separation of videos/audios by link. Check the complete list here
- Audio Downloader
- Kaggle Support
- In your Google Drive account create 2 folders. One for the audios you are going to separate and another where the separated files will be saved.
- Upload all the audios you want to separate into the folder you created.
- Run the first cell and give it access permissions to Google Drive.
- Place the paths to the folders you created in Google Drive or YouTube video/short link, then select the model you want to use and its parameters, then run the cell.
- Now you have the separated audios in the output folder!
Extra:
You can download the audio of a YouTube video by entering the link of the video, the path where it will be saved (it is recommended that it be the same where you save the audios that you are going to separate), audio format and the name of the audio (give it the name you want)
If you want to participate and help me with this project feel free to create an issue if something goes wrong or make a pull request to improve this project.
Any type of contribution is welcome 💖
If you liked this Colab you can star this repository. I will appreciate a lot 💖💖💖
You can donate to the original UVR5 project here:
