Projects sharing features with DeepSeek OCR

Qwen2-VL is a multimodal large language model and vision language model designed to process and reason across text, images, and video content. It functions as a visual reasoning engine and a visual agent framework, capable of interpreting visual data to perform object detection, document parsing, and spatial reasoning. The model is distinguished by its ability to act as a video understanding model, processing hour-long videos with second-level indexing and event recall. It further differentiates itself through a visual agent capability that interacts with software interfaces and robotic hardw

This project is a PyTorch-based framework and toolkit for scene text recognition. It provides a deep learning pipeline for extracting characters and words from images of natural environments, covering the full process from training data preparation to model validation. The framework functions as a standardized benchmark for measuring the accuracy and inference speed of text recognition models. It includes tools for calculating recognition accuracy and measuring GPU processing time per image to evaluate model performance across consistent datasets. The system incorporates visual and sequentia

Paper2gui is a multi-modal AI toolkit and model GUI wrapper designed to deploy and run various artificial intelligence models through a visual interface. Its primary purpose is to provide a way to execute complex AI research papers and models without requiring manual software installation or coding. The project distinguishes itself by using a wrapper-based model interface that abstracts command line arguments into visual input fields, utilizing template-driven UI generation to create parameter sliders and forms based on the specific requirements of the underlying model. It includes a centrali

Textract is a multi-format text extraction tool and parser. It provides a unified interface to extract plain text from a variety of sources, including documents, images, and audio files. The system functions as a document content parser for PDFs and spreadsheets, an image text extractor using optical character recognition, and a speech-to-text transcriber for audio recordings.

LLaVA is a multimodal large language model architecture designed to process and interpret both image and text inputs to generate natural language responses. It functions as a research-oriented platform for visual instruction tuning, providing a framework to align language models with human intent through training on diverse datasets of paired images and text queries. The system distinguishes itself through a specialized vision-language training pipeline that connects visual data to language models using projection layers and instruction-based fine-tuning. It supports distributed inference by

Janus is a multimodal large language model and unified framework that integrates visual understanding and image generation within a single neural network. It functions as both a visual understanding model for analyzing images and a text-to-image generator. The system uses a unified transformer backbone and a multimodal latent space to bridge the gap between text and visual data. This architecture employs decoupled visual encoding and cross-modal tokenization to separate the paths for discriminative understanding and generative tasks, representing images as grids of discrete codes. The projec

MiniCPM-V is a multimodal large language model and vision-language system designed for complex visual and linguistic understanding. It functions as an on-device AI model, providing the capacity to process text, images, and video as a compact neural network. The project is specifically developed as an edge AI framework, utilizing quantization and weight sharding to run on memory-constrained mobile chipsets. This allows for the deployment of multimodal intelligence directly on mobile operating systems for local inference. Its capabilities cover multimodal content analysis of high-resolution im

MiniCPM-o is a multimodal large language model designed to function as a real-time conversational assistant on edge devices. By mapping text, image, video, and audio inputs into a unified latent space, the system enables simultaneous cross-modal reasoning and full-duplex interaction. It is built as an edge-side inference engine, utilizing quantized model weights to maintain high-performance processing on consumer hardware. The system distinguishes itself through its integrated speech synthesis and voice cloning capabilities, which allow for the generation of expressive, personalized vocal out

InternVL is a vision-language model framework that fuses a visual encoder with a large language model to translate image features into textual tokens for reasoning. It provides a system for multimodal inference and dialogue, enabling the processing of images and text to answer questions or generate descriptions. The project is distinguished by its high-resolution image processing, which uses dynamic tiling to maintain detail for images up to 4K resolution, and its chain-of-thought visual reasoning for solving complex mathematical and spatial problems. It also supports temporal frame sampling

Minigo is a TensorFlow-based reinforcement learning engine designed to master the game of Go. It functions as a comprehensive system for training neural networks to predict board policies and game outcomes, utilizing a model trainer to generate self-play data and optimize weights. The project is distinguished by its ability to perform large-scale game simulations using Kubernetes to distribute worker nodes across CPU, GPU, and TPU hardware. It employs a Monte Carlo Tree Search implementation to identify optimal moves and supports specialized hardware acceleration, including inference on Edge

Dolphin is a multimodal layout analyzer and image-to-structure converter that transforms photographed or digital document images into machine-readable structured data. It functions as an LLM document parser, utilizing vision-language models to simultaneously predict spatial layout and text content. The system is designed as a concurrent document processor, employing parallel document parsing to process multiple elements across distributed compute nodes. This high-throughput approach reduces the total time required to convert large volumes of images into structured formats. The project covers

mmocr is a PyTorch-based optical character recognition framework designed for training and deploying text detection, recognition, and key information extraction models. It serves as a comprehensive toolbox for scene text detection and recognition, providing specialized libraries for locating text regions and converting visual text into machine-encoded strings. The project distinguishes itself through a research framework for key information extraction and advanced text spotting capabilities. These include point-based spotting using transformers and the use of parameterized Bezier curves to id

This project is an optical character recognition tool designed to extract hardcoded subtitles from video frames and convert them into synchronized subtitle files. It functions as a text processor that transforms embedded visual text into a written format to improve video accessibility and translation. The system uses graphics processing units to increase the speed and accuracy of text recognition. It includes a subtitle cleaning tool that applies custom mapping configurations to filter out watermarks, channel logos, and duplicate lines from the extracted text. The tool supports batch process

Tesseract is an optical character recognition engine and tool designed to convert printed or handwritten text from images into machine-readable digital text. It functions as a multilingual text extractor and a document digitization pipeline that transforms scanned images into structured digital formats. The project includes a framework for training custom scripts and language-specific models, allowing the engine to recognize new languages or unique fonts through custom training data. Its capabilities cover automated text extraction, digital archive digitization, and the export of recognized

EasyOCR is a deep learning-based computer vision library designed to perform optical character recognition on images and video frames. It functions as a comprehensive pipeline that automates the transformation of visual text into machine-readable strings, enabling the digitization of physical documents, forms, and receipts into searchable data. The engine distinguishes itself through a multi-stage processing workflow that combines convolutional neural networks for spatial feature extraction with sequence-based decoding mechanisms. This architecture allows the system to identify and interpret

This application is a cross-platform desktop utility designed for automated translation, optical character recognition, and speech synthesis. It functions as a modular client that integrates various local and remote language services, allowing users to process text through hotkeys, clipboard monitoring, or direct input. The software distinguishes itself through a plugin-based architecture and a built-in automation framework. By exposing a local network interface, it enables external applications and scripts to programmatically trigger its translation and recognition workflows. Users can furth

Umi-OCR is an optical character recognition engine designed to convert visual text from images and documents into machine-readable character data. It functions as a local-first toolkit, processing all visual data directly on the host machine using embedded neural network models to maintain privacy and offline availability. The project distinguishes itself through its focus on automated document digitization and integrated barcode and QR code decoding. By utilizing a modular, Python-based orchestration layer, it enables users to transform static image files and multi-page documents into search

Stirling-PDF is a self-hosted document processing suite designed for secure, private file management. It functions as a comprehensive transformation engine that executes complex operations—such as merging, splitting, converting, and redacting documents—directly on the host machine. The platform provides both a browser-based interface for interactive editing and a programmatic, API-first architecture that allows for the automation of document workflows through standard HTTP requests. The project distinguishes itself through its focus on private, infrastructure-agnostic deployment and granular

Tesseract is a neural network-based optical character recognition engine designed to convert scanned images and digital documents into machine-readable, searchable text. It functions as both a command-line utility for automating large-scale digitization workflows and a cross-platform library that can be embedded into desktop, mobile, or server-side applications. By utilizing long short-term memory networks, the engine provides robust text extraction across more than one hundred languages and dozens of scripts. The project distinguishes itself through a sophisticated document layout analysis f

ml-ferret is a multimodal large language model framework and visual reasoning engine designed to reason about images and user interfaces. It functions as a UI grounding model and referring expression comprehension tool that maps natural language descriptions to precise pixel coordinates. The system focuses on high-resolution image analysis to identify and locate specific interface components. It employs multi-resolution image processing and region-aware visual encoding to preserve detail across different aspect ratios, enabling the model to analyze spatial relationships and functional layouts

MiniGPT-4 is a multimodal AI framework and large language model that integrates vision encoders with language models to process and reason about combined image and text inputs. It functions as a vision-language model capable of image-based conversational AI, visual question answering, and multimodal logical reasoning. The project utilizes a pretrained vision-language integration strategy that connects a vision encoder to a language model via a linear projection layer. This approach employs frozen-backbone training to align visual representations with linguistic tokens while keeping the primar

PyMuPDF is a comprehensive PDF manipulation library and document analysis tool. It serves as a text extraction tool, OCR engine, and image converter, providing a programmatic interface to edit, merge, split, and optimize PDF and Office documents. The project distinguishes itself through high-performance capabilities, including the use of C-bindings for low-level manipulation and parallelized page processing to accelerate workloads. It provides specialized conversion paths, such as transforming PDF content into Markdown for retrieval-augmented generation and large language model pipelines. It

PDF-Extract-Kit is a document extraction toolkit designed to convert PDF documents into structured formats such as Markdown, HTML, and LaTeX. It functions as a multi-stage parsing framework that combines a document layout analyzer, a formula recognition engine, an OCR text extractor, and a table extraction system. The project focuses on recovering complex document elements by translating images of mathematical formulas and tabular structures into editable source code. It utilizes model-driven layout analysis to identify structural elements in reports and textbooks while ignoring noise like wa

Botasaurus is a Python web scraping framework and headless browser automation system used to build scalable data extraction tools. It functions as a web data extraction tool and OCR document parser, converting website content, images, and PDF files into structured formats such as JSON, CSV, and Excel. The framework distinguishes itself by providing a scraper management interface that allows Python functions to be wrapped in a web-based UI or deployed as standalone desktop applications. This enables non-technical users to trigger extraction jobs and manage tasks via a graphical interface or RE

Dango-Translator is an OCR translation system and multi-engine translation client designed to extract text from images or screens and replace it with translated content. It functions as an image text translator and real-time screen translator, utilizing optical character recognition to convert text between different languages automatically. The software distinguishes itself through coordinate-based image typesetting and a glossary manager. These tools allow for the replacement of original image content with translated text in the same area and the use of specialized dictionaries to ensure con

OCRmyPDF is a tool for converting image-based PDF files into machine-readable documents by adding a searchable text layer via optical character recognition. It functions as a multi-language processor capable of detecting and extracting text in over 100 different languages using linguistic data packs. The software includes a PDF image optimizer to remove image artifacts and correct page skew to improve recognition accuracy. It also provides a converter to transform scanned documents into the PDF/A standard for long-term digital archiving. The system manages PDF optimization by compressing emb