zai-org/GLM-OCRGitHub
when you want an Apache-2.0 VLM-based OCR/document parser as a direct model alternative.
GLM-OCR: Accurate × Fast × Comprehensive
- 7.3k
- Python
- Apache-2.0
active6mo ago
bytedance/Dolphin Alternatives
document image parsing
Dolphin is an ACL 2025 VLM-based universal document parsing model that classifies document type, analyzes layout with reading order, and extracts text, formulas, tables, and code blocks into markdown.
Drop-in peers
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Ucas-HaoranWei/GOT-OCR2.0GitHub
when you want a unified end-to-end VLM OCR model as a direct alternative for document parsing.
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
- 8.2k
- Python
- none
dormant1.7y ago
Same job, different approach
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
breezedeus/Pix2TextGitHub
when you need an MIT-licensed, small-model document parser that is lightweight and easy to integrate.
An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.
- 3.2k
- Jupyter Notebook
- MIT
slowing8mo ago
agentii-ai/DocMeldGitHub
when you want a lightweight pipeline focused on extracting structured metadata and page content from papers/books.
Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, and AI-enriched metadata from research papers and books. Generate PRDs, workflows, topic clusters, and Claude Code skills from PDFs. No OCR required.
- 100
- Python
- none
active3mo ago
RapidAI/RapidDocGitHub
when you want an Apache-2.0 ONNX-based pipeline for PDF-to-markdown/JSON with efficient CPU inference.
A high-performance, open-source PDF data extraction tool. 一站式开源高性能数据提取工具，将复杂 PDF 文档转换为 Markdown 和 JSON 格式，使用onnx模型。
- 213
- Python
- Apache-2.0
active2mo ago
opendatalab/MinerUGitHub
when you need a mature, feature-rich pipeline for PDF/Office-to-markdown with strong community support.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
- 78.2k
- Python
- NOASSERTION
active2mo ago
Older generation, or narrower
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
UglyToad/PdfPigGitHub
when you need a C# library for direct text extraction from PDFs without ML inference.
Read and extract text and other content from PDFs in C# (port of PDFBox)
- 2.5k
- C#
- Apache-2.0
active2mo ago
adrienjoly/npm-pdfreaderGitHub
when you need a Node.js library for text and table extraction from PDFs without deep-learning dependencies.
🚜 Parse text and tables from PDF files.
- 704
- HTML
- MIT
slowing9mo ago
monniert/docExtractorGitHub
when you are working with historical documents and need a specialized off-the-shelf element extractor.
(ICFHR 2020 oral) Code for "docExtractor: An off-the-shelf historical document element extraction" paper
- 89
- Python
- MIT
dormant3.4y ago
modesty/pdf2jsonGitHub
when you need a zero-dependency Java server-side PDF-to-JSON/text converter without ML.
converts binary PDF to JSON and text, for server-side PDF processing and command-line use. Zero dependency.
- 2.2k
- Java
- NOASSERTION
active6mo ago
mindee/doctrGitHub
when you need a focused OCR library for text detection and recognition, not full layout/markdown parsing.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.
- 6.3k
- Python
- Apache-2.0
active2mo ago
clovaai/deep-text-recognition-benchmarkGitHub
when you need a classic deep-learning text recognition model for standalone OCR tasks without layout parsing.
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
- 3.9k
- Jupyter Notebook
- Apache-2.0
dormant2.6y ago
End-user tools
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
PSPDFKit/pdf-to-markdownGitHub
when you want a simple CLI wrapper for PDF-to-Markdown without deploying a large model.
Standalone CLI wrapper and docs for Nutrient's PDF-to-Markdown extractor
- 321
- Shell
- NOASSERTION
active2mo ago
Listed as an alternative to
These projects were analysed and named Dolphin among their alternatives. The relationship is not symmetric — how Dolphin rates them is a separate judgement, made when Dolphin is analysed in its own right.
baidu/Unlimited-OCRGitHub
calls Dolphin “Same class of VLM document parser; pick if you prefer a model with ACL-2025 anchor prompting and can check its license.”
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
24.3kPythonactive
studio-dots-ai/dots.ocrGitHub
calls Dolphin “choose when you want a peer research model for complex document layout benchmarks and can accept an unasserted license.”
Multilingual Document Layout Parsing in a Single Vision-Language Model
9.1kPythonactive
Ucas-HaoranWei/GOT-OCR2.0GitHub
calls Dolphin “document image parsing model, direct alternative for formatting-aware extraction”
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
8.2kPythondormant
zai-org/GLM-OCRGitHub
calls Dolphin “Choose for a research-focused document image parser using a different anchor-prompting approach.”
GLM-OCR: Accurate × Fast × Comprehensive
7.3kPythonactive
Yuliang-Liu/MonkeyOCRGitHub
calls Dolphin “LMM-based document image parser, similar capability to MonkeyOCR”
A lightweight LMM-based Document Parsing Model
6.6kPythonactive
oomol-lab/pdf-craftGitHub
calls Dolphin “Vision-language model for document image parsing; choose when you want to use this specific model directly for Markdown generation.”
PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.
6.2kPythonactive
JaidedAI/EasyOCRGitHub
calls Dolphin “Choose when you are researching document image parsing and want the ACL 2025 baseline, not a maintained production OCR.”
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
29.9kPythonslowing
opendataloader-project/opendataloader-pdfGitHub
calls Dolphin “Choose if you are doing research or want a state-of-the-art document image parsing model; it is not a turnkey library.”
PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.
28.6kJavaactive
datalab-to/suryaGitHub
calls Dolphin “research-grade anchor-prompting parser, less mature but distinct architecture.”
OCR, layout analysis, reading order, table recognition in 90+ languages
21.3kPythonactive
firecrawl/pdf-inspectorGitHub
calls Dolphin “choose it for a research-grade document-image parsing model, not a lightweight local library.”
Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
17.9kRustactive
StarTrail-org/PixelRAGGitHub
calls Dolphin “Use for academic document image parsing via heterogeneous anchor prompting, not as a search engine.”
The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
9.7kPythonactive
RapidAI/RapidOCRGitHub
calls Dolphin “Choose for a research-grade document image parsing model with heterogeneous anchor prompting if you accept working from an unreleased codebase.”
📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
7.6kPythonactive
pdfminer/pdfminer.sixGitHub
calls Dolphin “choose when input is scanned page images and you need deep-learning layout parsing into Markdown, not PDF content streams”
Community maintained fork of pdfminer - we fathom PDF
7.0kPythonactive
axa-group/ParsrGitHub
calls Dolphin “research model for document image parsing via deep learning, requires GPU and is not a maintained tool.”
Transforms PDF, Documents and Images into Enriched Structured Data
6.2kJavaScriptactive
Dicklesworthstone/llm_aided_ocrGitHub
calls Dolphin “Same document image parsing goal with a different model architecture.”
Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs
3.0kPythonactive
docling-project/doclingGitHub
calls Dolphin “if you need a research-grade document image parsing model for specific image inputs”
Get your documents ready for gen AI
66.4kPythonactive
datalab-to/markerGitHub
calls Dolphin “When you want to apply a specific research model for document image parsing.”
Convert PDF to markdown + JSON quickly with high accuracy
39.0kPythonactive
xberg-io/xbergGitHub
calls Dolphin “when you want to apply the specific ACL-2025 document-image-parsing model, not a general-purpose parser.”
A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured data from 101 formats (115 file extensions) plus code intelligence for 371 code languages. 15 language bindings — Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript — plus CLI, REST API, and MCP server.
9.2kRustactive
adithya-s-k/omniparseGitHub
calls Dolphin “choose it for experimenting with the ACL 2025 document image parsing model if you want SOTA research code, not a production tool.”
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
7.8kPythonslowing
Topdu/OpenOCRGitHub
calls Dolphin “A single document image parsing model from a paper, not a full toolkit, narrower than OpenOCR.”
OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful reproductions of the core implementations from a wide range of academic papers.
1.4kPythonactive