Music and Audio

Personalized stats for your Spotify profile.

Parses forensic artifacts from macOS file systems

Parse lyrics and add them into mp3 files (via id tags). Lyrics can then be viewed on iPhone, iTunes and other players.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Open source Spotify client that doesn't require Premium nor uses Electron! Available for both desktop & mobile!

Open source audio fingerprinting in .NET. An efficient algorithm for acoustic fingerprinting written purely in C

Open Lyrics Database website

ONNX deployment of the CREPE pitch tracker

Online web based mel-spectrum, power spectrum, FFT analyzer for speech and music processing

Official PyTorch implementation of Contrastive Learning of Musical Representations

Official Code of "A Semi-Supervised Deep Learning Approach to Dataset Collection for Query-by-Humming Task" (ISMIR 2023)

Obsidian plugin to create high-quality transcriptions from markdown linked audio files

Object-oriented handling of audio data, with GPU-powered augmentations, and more.

nowplaying-RS Music Recommendation using Factorization Machines

NIPS2017 "Time Domain Neural Audio Style Transfer" code repository

Neural Symphony is a music player application like Spotify integrated with AI Technology - Neural Network Architecture. The aim of this project is to use the advantage of AI - Machine Learning is for

Network Analysis of Generalized Musical Spaces

My curated list of audio DSP and plugin development resources

MusicMetaLinker - Entity Linking and Knowledge Augmentation library for music metadata

MusicGen is a simple and controllable model for music generation. It is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. Unlike existing methods like MusicLM, MusicGen doesn't require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. By introducing a small delay between the codebooks, the authors show they can predict them in parallel, thus having only 50 auto-regressive steps per second of audio. They used 20K hours of licensed music to train MusicGen. Specifically, they relied on an internal dataset of 10K high-quality music tracks, and on the ShutterStock and Pond5 music data.

MusicBrainz Picard plugins

musical_score music segmentation in audio domain

musical_keyboard symbolic musical datasets

Music Tools is an all-in-one solution for music enthusiasts who want to easily search, download, and manage their music.

Music tagger with GUI that parses wikipedia for information. Can also download album art and lyrics.

Music Structure Analysis Framework

Music remixer based on MusicGen-Chord

Music Mood Classification on the Million Song Dataset

Music genre classification system built on a convolutional neural network trained on Mel-spectrograms of 3-second audio samples.

Music classification using music information retrieval techniques and machine learning