Lists (1)
Starred repositories
An OCRmyPDF plugin that uses docTR (Document Text Recognition by Mindee) as backend.
OnnxTR a docTR (Document Text Recognition) library Onnx pipeline wrapper - for seamless, high-performing & accessible OCR
ShabbyPages is a state-of-the-art corpus of born-digital document images with both ground truth and distorted versions appropriate for use in training models to reverse distortions and recover to o…
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
Continuation of an abandoned project fast-coco-eval
A Large-scale Dataset for training and evaluating model's ability on Dense Text Image Generation
Coding super-intelligence to find the most optimized Python code. Use it to optimize existing codebases or new Pull requests as a GitHub Action or a VS Code Extension.
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]
The simplest, fastest repository for training/finetuning small-sized VLMs.
MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining
Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you alre…
Get your documents ready for gen AI
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.
This package contains the original 2012 AlexNet code.
The python library for real-time communication
Toolkit for linearizing PDFs for LLM datasets/training
Bazzite makes gaming and everyday use smoother and simpler across desktop PCs, handhelds, tablets, and home theater PCs.
A OCR labeling tool - made for docTR
[CAAI AIR'24] Bilateral Reference for High-Resolution Dichotomous Image Segmentation
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.
Fully open reproduction of DeepSeek-R1
⚡ Create handwritten documents from text with a Neural Network!
File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.
Use this tool to label forms, bounding boxes, and assigning types to annotations
A modern and customizable python UI-library based on Tkinter
DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding