Production First and Production Ready End-to-End Speech Recognition Toolkit

A virtual file system implementation in modern C#.

A cross-platform abstract/virtual filesystem framework with many built-ins filesystems for .NET

Sparsity-aware deep learning inference runtime for CPUs

YoloDotNet - A C# .NET 8.0 project for Classification, Object Detection, OBB Detection, Segmentation and Pose Estimation in both images and videos.

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

A collection of artifacts and samples to help developers build on and for Windows.

Official PyTorch implementation of BigVGAN (ICLR 2023)

ONNX Script enables developers to naturally author ONNX functions and models using a subset of Python.

PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.

Fast and memory-efficient exact attention

A website to provide FAQ support for SlimeVR

Project Trainee

A very simple tool for situations where optimization with onnx-simplifier would exceed the Protocol Buffers upper file size limit of 2GB, or simply to separate onnx files to any size you want.

Simple tool to combine(merge) onnx models. Simple Network Combine Tool for ONNX.

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.

An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement

[ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Concrete: TFHE Compiler that converts python programs into FHE equivalent

Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models and Concrete

HE-MAN – Homomorphically Encrypted MAchine learning with oNnx models and TenSEAL

Microsoft SEAL is an easy-to-use and powerful homomorphic encryption library.

Low latency application audio routing for Windows

SubFix: Efficient Web-Based Audio Subtitle Editing and Multilingual Automatic Annotation Tool.

🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.

AI Audio Datasets (AI-ADS) 🎵, including Speech, Music, and Sound Effects, which can provide training data for Generative AI, AIGC, AI model training, intelligent audio tool development, and audio a…

一个快速制作语音数据集的可视化工具