A powerful tool for creating fine-tuning datasets for LLM

🚀 Easier & Faster YOLO Deployment Toolkit for NVIDIA 🛠️

基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.

Local UI to run and train LLMs and diffusion models, including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, FLUX and more.

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

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 。

A light and fast one class detection framework for edge devices. We provide face detector, head detector, pedestrian detector, vehicle detector......

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

This repository contains datasets and baselines for benchmarking Chinese text recognition.

pytorch crnn with centerloss to solve the near word problem

基于Pytorch的OCR工具库，支持常用的文字检测和识别算法

(WIP)The deployment framework aims to provide a simple, lightweight, fast integrated, pipelined deployment framework for algorithm service that ensures reliability, high concurrency and scalability…

PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

Chatbot继续沿着LLM前进，近期更新小参数量SLM的和训练脚本，支持本地训练。新增ChatAgent,实现各种有实际场景价值的Agent实现。

fay是一个帮助数字人（2.5d、3d、移动、pc、网页）或大语言模型（openai兼容、deepseek）连通业务系统的agent框架。

mmd_tools is a blender addon for importing Models and Motions of MikuMikuDance.

MMD Tools is a Blender addon for importing/exporting Models and Motions of MikuMikuDance.

🍀 Another Chinese chatbot implemented in PyTorch, which is the sub-module of intelligent work order processing robot. 👩‍🔧

中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、IT词库、财经词库、成语词库、地名词库、…

APAP FOR IMAGE STITCHING

As-Projective-As-Possible (APAP) Image Stitching with Moving DLT (CVPR 2013) - Python Implementation

As-Projective-As-Possible (APAP) Image Stitching with Moving DLT - Python Implementation

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

基于pytorch的ocr算法库，包括 psenet, pan, dbnet, sast , crnn

AdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.

Crack LeetCode, not only how, but also why.

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

A synthetic data generator for text recognition with arabic and persian strings support