Stars
An Algorithmic Information Theory Library (And Information-theory broadly); Implements numerous approximations, estimations, as well as a comprehensive MC-AIXI Agent & Model Ensemble platform.
Semi-Supervised Contrastive Learning for music classification - towards HIL-representation learning.
SuperCollider pluging to send audio over RTP using GStreamer
Sound As Pure Form - a Forth-like language for audio synthesis using lazy lists and APL-like auto-mapping.
A terminal spreadsheet multitool for discovering and arranging data
The official code repo of "HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection"
✨✨Latest Advances on Multimodal Large Language Models
Source code for "MusCaps: Generating Captions for Music Audio" (IJCNN 2021)
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
Official implementation of "Contrastive Audio-Language Learning for Music" (ISMIR 2022)
A modular active learning framework for Python
An easy way to host your own AI API and expose alternative models, while being compatible with "open" AI clients.
Parallel (asynchronous) sparse coding implementation for obtaining sparse overcomplete word vectors
Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch
A Python 3 framework for Reservoir Computing with a scikit-learn-compatible API.
Community list of startups working with AI in audio and music technology
Original Perl Zigzag (tm) code referred to by Ted Nelson as "Azz" (Andrew's ZigZag)
Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
Command line tool to cut/extract parts of mp3 files at frame boundaries without requiring decoding or re-encoding. Imported from abandoned Sourceforge project 2020-09-09.