Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.

Fast and simple music and audio analysis using RNN in Python 🕵️‍♀️ 🥁

Python scripts accompanying the book "An Introduction to Audio Content Analysis" (www.AudioContentAnalysis.org)

Package for automatic beat-mixing of music files in Python 🐻🎚

Evolving Artificial Neural Networks for Cross-Adaptive Audio Effects

Extract frequency, power, width and dissonance of formants from wav files

Draw insights on Spotify users’ musical tastes and generate playlists tailored to either a single user or a group of users by analyzing their Top 100 tracks.

The aim of this project is to map and analyse the sentiments of different countries based on their music tastes over time. The data is presented in a web app coded in Python using the Plotly Dash package.

We developed an interpretable CNN for big five personality traits using human speech data. This project discovers the different frequency patterns of a human voice with respect to each five personality traits. This project will help us to understand the apparent personality of a human using his/her voice.

Code used in the article "SATIN: A Persistent Musical Database for Music Information Retrieval" by Yann Bayle, Pierre Hanna and Matthias Robine in CBMI 2017. SATIN is a MIR dataset for reproducible research.

Predict song genre using XGBoost gradient boosting

A simple music feature extractor for Deep Learning models

Python to generate a customized Spotify playlist based on historic user listening data

Audio feature extraction engine based on VAMP plugins

shazam like desktop app that you can select mp3 file and recognize the songs that matches the file and list them according to their similarity to the input file

ToneArcLib is an open-source audio analysis library that extracts expressive and structural features from music tracks using signal processing and ML techniques. Ideal for researchers, developers, and creatives building AI-driven music tools.

Temporal audio features extraction by Librosa.