Skip to content

Audio source separation + visual speaker identification using the discrete wavelet transform

Notifications You must be signed in to change notification settings

rmeghji/parrotfish

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

169 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CS1430 Final Project - Parrotfish

Team Members

  • Rayhan Meghji
  • Matthew McQuistion

Description

Our project combines audio source separation targeting timbral differences with visual speaker identification, where both methods employ the Discrete Wavelet Transform.

Usage

Our model can be used on Hugging Face Spaces to process video and audio files either separately or together, or locally with:

  • python src/main.py for audio
  • python src/vision/main_vision.py for video.

About

Audio source separation + visual speaker identification using the discrete wavelet transform

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •