Skip to content

End-to-end audio-visual speech enhancement pipeline — from preprocessing to deep learning model training to interactive app demo.

License

Notifications You must be signed in to change notification settings

Viderspace/Look2Listen

Repository files navigation

AV-Speech Enhancement Demo

Interactive demo for audio-visual speech enhancement model.

Local Setup

pip install -r requirements.txt
python app.py


# AV-Speech Enhancement Demo

Interactive demo for audio-visual speech enhancement model.

## Local Setup
```bash
pip install -r requirements.txt
python app.py
Deployment
Deployed on Hugging Face Spaces: [link]
Usage

Upload video or paste YouTube URL
Select time segment (max 15s)
Click on speaker's face
Process and download enhanced video

About

End-to-end audio-visual speech enhancement pipeline — from preprocessing to deep learning model training to interactive app demo.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages