🎵 UVR5 UI 🎵

If you liked this HF Space you can give me a ❤️

Try UVR5 UI using Colab here

Select the model

Select the output format

Segment size

Larger consumes more resources, but may give better results

32 4000

Override model default segment size instead of using the model default value

Override segment size

Overlap

Amount of overlap between prediction windows

2 10

Batch size

Larger consumes more RAM but may process slightly faster

1 16

Normalization threshold

The threshold for audio normalization

0.1 1

Amplification threshold

The threshold for audio amplification

0.1 1

Output only single stem

Input audio

Link

You can paste the link to the video/audio from many sites, check the complete list here

Input path

Output path

Output information

Stem 1

Stem 2

Select the model

Select the output format

Segment size

Larger consumes more resources, but may give better results

32 4000

Override model default segment size instead of using the model default value

Override segment size

Overlap

Amount of overlap between prediction windows

2 50

Batch size

Larger consumes more RAM but may process slightly faster

1 16

Normalization threshold

The threshold for audio normalization

0.1 1

Amplification threshold

The threshold for audio amplification

0.1 1

Output only single stem

Input audio

Link

You can paste the link to the video/audio from many sites, check the complete list here

Input path

Output path

Output information

Stem 1

Stem 2

Select the model

Select the output format

Hop length

Usually called stride in neural networks; only change if you know what you're doing

32 2048

Segment size

Larger consumes more resources, but may give better results

32 4000

Enable denoising during separation

Denoise

Overlap

Amount of overlap between prediction windows

0.001 0.999

Batch size

Larger consumes more RAM but may process slightly faster

1 16

Normalization threshold

The threshold for audio normalization

0.1 1

Amplification threshold

The threshold for audio amplification

0.1 1

Output only single stem

Input audio

Link

You can paste the link to the video/audio from many sites, check the complete list here

Input path

Output path

Output information

Stem 1

Stem 2

Select the model

Select the output format

Window size

Balance quality and speed. 1024 = fast but lower, 320 = slower but better quality

320 1024

Agression

Intensity of primary stem extraction

1 50

Enable Test-Time-Augmentation; slow but improves quality

TTA

Identify leftover artifacts within vocal output; may improve separation for some songs

Post process

Post process threshold

Threshold for post-processing

0.1 0.3

Mirror the missing frequency range of the output

High end process

Batch size

Larger consumes more RAM but may process slightly faster

1 16

Normalization threshold

The threshold for audio normalization

0.1 1

Amplification threshold

The threshold for audio amplification

0.1 1

Output only single stem

Input audio

Link

You can paste the link to the video/audio from many sites, check the complete list here

Input path

Output path

Output information

Stem 1

Stem 2

Select the model

Select the output format

Shifts

Number of predictions with random shifts, higher = slower but better quality

1 20

Segment size

Size of segments into which the audio is split. Higher = slower but better quality

1 100

Enable segment-wise processing

Segment-wise processing

Overlap

Overlap between prediction windows. Higher = slower but better quality

0.001 0.999

Batch size

Larger consumes more RAM but may process slightly faster

1 16

Normalization threshold

The threshold for audio normalization

0.1 1

Amplification threshold

The threshold for audio amplification

0.1 1

Input audio

Link

You can paste the link to the video/audio from many sites, check the complete list here

Input path

Output path

Output information

Stem 1

Stem 2

Stem 3

Stem 4

Stem 5

Stem 6

List filter

Filter and sort the model list by stem

Theme

Select the theme you want to use. (Requires restarting the App)

Textbox

UVR5 UI created by Eddycrack 864. Join AI HUB community.

python-audio-separator by beveradb.
Special thanks to Ilaria for hosting this space and help.
Thanks to Mikus for the help with the code.
Thanks to Nick088 for the help to fix roformers.
Thanks to yt_dlp devs.
Separation by link source code and improvements by Blane187.
Thanks to ArisDev for porting UVR5 UI to Kaggle and improvements.
Thanks to Bebra777228's code for guiding me to improve my code.
Thanks to Nick088, MrM0dZ, Ryouko-Yamanda65777, lucinamari, perariroswe, Enes, Léo and the_undead0 for helping translate UVR5 UI.
Thanks to vadigr123 for creating the images for the Discord Rich Presence.

You can donate to the original UVR5 project here

Built with Gradio logo