CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.

Script that identifies track title and artist from a list of MP3 files, thanks to audio fingerprinting.

Dockerized benchmark model & API for classifying music by genre based on TensorFlow and Essentia

A demo for fingerprint of python implement

About I have taken the premade algorithm from the offical shazam research paper and try to implement it on our local dataset.

A deep learning model designed to distinguish human-made music from AI-generated music with a TKinter interface.

I have taken the premade algorithm from the offical shazam research paper and try to implement it on our local dataset.