Stars
FlexConv Pytorch Implementation with additional modules
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
An "awesome music theory" kinda wiki with books, resources and courses for studying everything about music and sound
A chord identifier and harmonizer for MIDI files
A multi-arch image provides one HTTP proxy endpoint with many concurrent tunnels to the Tor network.
MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …
🎚️ Open Source Audio Matching and Mastering
2021 ISMIR tutorial - music classification
Muzic: Music Understanding and Generation with Artificial Intelligence
Flax is a neural network library for JAX that is designed for flexibility.
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
efficient neural audio synthesis in the waveform domain
Write cross-platform native apps with React.js and JUCE
A prototype to model a way to create an entire repo using JUCE and CMake.
An All-MLP solution for Vision, from Google AI
Open standard for machine learning interoperability
A GPU-optional modular synthesizer in pytorch, 16200x faster than realtime, for audio ML researchers.
Audio processing by using pytorch 1D convolution network
CREPE: A Convolutional REpresentation for Pitch Estimation -- pre-trained model (ICASSP 2018)
Collection of audio-focused loss functions in PyTorch
Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch
A pytorch implementation for paper 'Exploring Simple Siamese Representation Learning'
Evaluation functions for music/audio information retrieval/signal processing algorithms.
A super simple API for reading the iTunes content.
Code for our paper "Towards realistic MIDI instrument synthesizers" (https://cs.stanford.edu/~rjcaste/research/realistic_midi.pdf)
A modern and transparent way to use Windows VST2, VST3 and CLAP plugins on Linux
A high-quality speech analysis, manipulation and synthesis system