DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Nix, the purely functional package manager

Easy to use open source fast database for search | Good alternative to Elasticsearch now | Drop-in replacement for E in the ELK stack

🎛 🔊 A Python library for audio.

projectM - Cross-platform Music Visualization Library. Open-source and Milkdrop-compatible.

Eurorack modules

Plugin for Neural Amp Modeler

audible feedback on just how much your browsing feeds into google

Guitar plugin made with JUCE that uses neural networks to emulate a tube amplifier.

Praat in Python, the Pythonic way

Raspberry Pi guitar pedal using neural networks to emulate real amps and effects.

C++ functions matching the interface and behavior of python string methods with std::string

Sound As Pure Form - a Forth-like language for audio synthesis using lazy lists and APL-like auto-mapping.

WaveNet for virtual analog modeling, implemented as a real-time audio plugin using JUCE.

A simple reverb made with the JUCE DSP module

A node.js native library that provides access to Mac OS X Audio I/O as streams.

Cross platform minimal block based audio dsp library

A Wrapper Template for deploying Libtorch models in JUCE-based Audio/Midi Applications

Dynamic module for searching artists on musicbrainz