Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

Benchmarks of approximate nearest neighbor libraries in Python

Tools for merging pretrained large language models.

A cheap (around $20) DSP built using the Espressif ESP32-Lyrat development board.

Cheerp - a C/C++ compiler for Web applications - compiles to WebAssembly and JavaScript

Fix Play Integrity (and SafetyNet) verdicts.

ih8sn allows you to modify system properties at runtime.

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

This tool provides an efficient implementation of the continuous bag-of-words and skip-gram architectures for computing vector representations of words. These representations can be subsequently us…

Run Ubuntu GUI on your termux with much features.

中文词典 / 中文詞典。Chinese / Chinese-English dictionaries.

JSON data files parsed from the Unicode Han Database (Unihan)

한국어문회 등급별 선정한자 CSV 데이터셋

Hanja Understanding Evaluation Dataset

For review of draft Unihan database changes, removals, and additions by experts.

Use HTML Canvas API but produce an SVG

Translates HTML5 Canvas draw commands to SVG

This is stuntman running on openwrt. Compliant with the latest RFCs including 5389, 5769, and 5780. Also includes backwards compatibility for RFC 3489.

Lightweight STUN/TURN server

WebRTC and ORTC implementation for Python using asyncio

BananaBread is a C++ 3D game engine that runs on the web using JavaScript+WebGL+HTML

ScreenPen is a simple screen annotation software that allows drawing directly on the screen.

speech self-supervised representations

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.

We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multi…

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis