vlm-ocr

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

A hub for various industry-specific schemas to be used with VLMs.

Open-source tools for training and evaluating Vision Language Models for OCR

Agentic RAG Harness for long documents, Tree and Graph based reasoning. Cited answers down to the pixel

Yet another self-hosted AI voice assistant. GlaDOS' blazing fast pipeline with Kokoro TTS voice and vision.

Redact PDF/image-based documents, Word, or CSV/XLSX files using a graphical user interface. Demo: https://huggingface.co/spaces/seanpedrickcase/document_redaction or with try with VLMs: https://huggingface.co/spaces/seanpedrickcase/document_redaction_vlm

Benchmarking Vision-Language Models on OCR tasks in Dynamic Video Environments

IFTG (ImageFromTextGenerator) is a Python package that simplifies creating robust datasets for OCR models. Generate images from text, apply over 10 built-in noise effects, and customize fonts and layouts. IFTG supports all languages and offers endless noise combinations, including custom noise creation.

Beautiful, minimal formula OCR desktop app powered by vision-language model APIs. Capture, edit, render, and copy LaTeX anywhere.

Production grade Document AI workflows run on Tensorlake

OCR it on macOS with DeepSeek-OCR

🏆 智能证书识别与保研加分系统 - End-to-end certificate recognition & structured extraction powered by FireRed-OCR + Qwen3-VL-4B

Document image retrieval via MCP or API for agentic systems using semantic embeddings, YOLO, and VLM classification.

Korean olmOCR

Performance and speed-focused, VLM-powered eBook and image text extraction, and visual scanning engine.

The CyberTech VLM Detector is a computer vision system designed to run entirely on edge devices, without requiring cloud access. The system uses vision-language models (VLM) to detect and locate objects in images based on natural language commands and development, including my creation of HIM™ and MAIC™

DocuLingo is a powerful document parsing tool built with multimodal large language models to enhance RAG (Retrieval Augmented Generation) workflows.

Digitizing various Bantu languages' dictionaries using OCR and Vision LLMs following Cross-Linguistic Data Format (CLDF), as part of the SocioBaGS Project. Built with guidance from Jr. Prof. Annemarie Verkerk and Ph. D. Rita Popova.

A lightweight tool that converts handwritten Rnote papers into well-structured documents (Markdown/LaTeX/Typst) using VLMs

Hackathons 2026 du master Humanités numériques (Enc-PSL) - résultats du pôle HTR