SGLang is a fast serving framework for large language models and vision language models.

Real-time neural network inferencing

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

🔊 Text-Prompted Generative Audio Model

🦜🔗 Build context-aware reasoning applications

Transformer related optimization, including BERT, GPT

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva

A C library for reading and writing sound files containing sampled audio data.

A collection of tools (written in C) to do interesting things with sound files

Official code for Wav2Seq

RAPIDS Memory Manager

A simple memory manager for CUDA designed to help Deep Learning frameworks manage memory

A lightning fast Finite State machine and REgular expression manipulation library.

Grapheme to phoneme model for PyTorch

Fast Neural Machine Translation in C

A standard library for use in specifying protocol buffer APIs.

PyTorch CTC Decoder bindings

Command-line tools for working with Architecture Decision Records

Variational Bayes HMM over x-vectors diarization

gRPC to JSON proxy generator following the gRPC HTTP spec

Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"

Automatic differentiation with weighted finite-state transducers.

A header-only StatsD client implemented in C

CNCF Jaeger, a Distributed Tracing Platform

OpenTelemetry Go API and SDK

OpenTelemetry Java SDK