Stars
基于transformer的ocr识别,在公章(印章识别, seal recognition)拓展应用
Recognition of Various Common Seal Scans in Complex Environments
开源易用的中文离线OCR,识别率媲美大厂,并且提供了易用的web页面及web的接口,方便人类日常工作使用或者其他程序来调用~
Official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution"
超轻量级中文ocr,支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) crnn(2.5M) anglenet(378KB)) 总模型仅4.7M
xmnlp:提供中文分词, 词性标注, 命名体识别,情感分析,文本纠错,文本转拼音,文本摘要,偏旁部首,句子表征及文本相似度计算等功能
Wiseflow is an agile information mining tool that extracts concise messages from various sources such as websites, WeChat official accounts, social platforms, etc. It automatically categorizes and …
hiprint for Vue2/Vue3 ⚡打印、打印设计、可视化设计器、报表设计、元素编辑、可视化打印编辑
基于python的网页自动化工具。既能控制浏览器,也能收发数据包。可兼顾浏览器自动化的便利性和requests的高效率。功能强大,内置无数人性化设计和便捷功能。语法简洁而优雅,代码量少。
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction
GraphRAG-Ollama-UI GraphRAG4OpenWebUI 融合版(有gradio webui配置生成RAG索引,有fastapi提供RAG API服务)
A Comprehensive Toolkit for High-Quality PDF Content Extraction
A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具,支持PDF/网页/多格式电子书提取。
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
OCR, layout analysis, reading order, table recognition in 90 languages
A modern download manager that supports all platforms. Built with Golang and Flutter.
A modular, reusable university course for Rust
Slint is a declarative GUI toolkit to build native user interfaces for Rust, C , or JavaScript apps.
🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Azure / DeepSeek), Knowledge Base (file upload / knowledge manageme…
A simple zero-config tool to make locally trusted development certificates with any names you'd like.
【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models
Ergonomic and modular web framework built with Tokio, Tower, and Hyper
Out-of-Core hybrid Apache Arrow/NumPy DataFrame for Python, ML, visualization and exploration of big tabular data at a billion rows per second 🚀