NVR with realtime local object detection for IP cameras

HandBrake's main development repository

【间隙·树·排序算法】 对OCR结果或PDF提取的文本进行版面分析，按人类阅读顺序进行排序。

Quickly and securely sync clipboard, transfer files and directories between devices. 快速安全的同步剪切板，传输文件或文件夹

Universal markup converter

locally hosted web application that allows you to perform various operations on PDF files

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

An open-source cross-platform alternative to AirDrop

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

🤖 Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your p…

Convert PDF to markdown quickly with high accuracy

Build high-performance AI models with modular building blocks

Given a scholarly PDF, extract figures, tables, captions, and section titles.

My implementation of Kosmos2.5 from the paper: "KOSMOS-2.5: A Multimodal Literate Model"

A build-it-yourself, 6-wheel rover based on the rovers on Mars!

[🔥updating ...] AI 自动量化交易机器人 AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant

bigsai的数据结构与算法、LeetCode图解、剑指offer图解文章专栏，致力于最好懂的数据结构与算法专栏

The official Sentry SDK for iOS, tvOS, macOS, watchOS.

biblos.app

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

pix2tex: Using a ViT to convert images of equations into LaTeX code.

OCR图片转文字识别软件，完全离线。截屏/批量导入图片，支持多国语言、合并段落、竖排文字。可排除水印区域，提取干净的文本。基于 PaddleOCR 。

Nougat is a Meta AI's revolutionary OCR model designed to transcribe scientific PDFs into an easy-to-use Markdown format.

PDFio is a simple C library for reading and writing PDF files.

Telegram-iOS

A collection of machine learning examples and tutorials.

李跳跳自定义规则

缠中说禅技术分析工具；缠论；股票；期货；Quant；量化交易

A Conversational Assistant equipped with synthetic voices including J.A.R.V.I.S's. Powered by OpenAI and IBM Watson APIs and a Tacotron model for voice generation.