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.

Facebook AI Research's Automatic Speech Recognition Toolkit

Enabling PyTorch on XLA Devices (e.g. Google TPU)

SLING - A natural language frame semantics parser

A domain specific language to express machine learning workloads.

Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE

PyTorch CTC Decoder bindings

Fast BPE

Fast Block Sparse Matrices for Pytorch

PyTorch C++ Reinforcement Learning

Pytorch C++ Library

Fast and customizable text tokenization library with BPE and SentencePiece support

Implementation code for ICML '17 paper "Deep Temporal Reasoning for Dynamic Knowledge Graphs"

SparseMAP: differentiable sparse structure inference