Stars
A scikit-learn compatible neural network library that wraps PyTorch
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing …
Stable diffusion for real-time music generation
Uses some known methods that attempt to minimize tracking in Windows 10
Audio Dataset for training CLAP and other models
Open-Unmix - Music Source Separation for PyTorch
Shared data types for building collaborative software
Graph-oriented live coding language and music/audio DSP library written in Rust
Word2Wave: a framework for generating short audio samples from a text prompt using WaveGAN and COALA.
Deep InfoMax (DIM), or "Learning Deep Representations by Mutual Information Estimation and Maximization"
Mobile/Web app for the control of sound spatialization
COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations
A brief tutorial on the Wasserstein auto-encoder
PyTorch code for training and evaluating MOVE, musically-motivated version embeddings
3D-DCGAN trained on a corpus of 3D printable objects - as a result, the generations are usually 3D printable
Modified implementation of DCGAN focused on generative art. Includes pre-trained models for landscapes, nude-portraits, and others.
scikit-learn cross validators for iterative stratification of multilabel data
Unsupervised Domain Adaptation for Acoustic Scene Classification with Wasserstein Distance
WebGL-powered Parallel Large-scale Graph Layout Visualization Framework
Node for Max with Tensorflow.js example
A platform for playing generative music in the browser.
Pronounced as "musician", musicnn is a set of pre-trained deep convolutional neural networks for music audio tagging.
A Python nearest neighbor descent for approximate nearest neighbors
Web-based application for exploring Freesound content with graph visualisation [WIP]
Code for Yun Wang's PhD Thesis: Polyphonic Sound Event Detection with Weak Labeling