Cross-platform, customizable ML solutions for live and streaming media.

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.

A toolkit for making real world machine learning and data analysis applications in C++

Unsupervised text tokenizer for Neural Network-based text generation.

Fast inference engine for Transformer models

KenLM: Faster and Smaller Language Model Queries

PyTorch CTC Decoder bindings

A Fast Sequence Transducer Implementation with PyTorch Bindings

Signapse is an open source software tool for helping everyday people learn sign language for free!