Skip to main content
ToolPotion
AI Advisor
Submit a Tool (Free)

Surya OCR 2.5

Surya OCR 2.5 is a powerful 689M parameter image-text-to-text model designed for document intelligence. It offers high accuracy, fast throughput, and multilingual support for OCR, layout analysis, and table recognition. This model can process various document types, extracting text, layout, and tables as HTML, making it ideal for advanced document processing tasks.

View Model
Share
View Model
Share

Surya OCR 2.5 is a state-of-the-art image-text-to-text model developed by Datalab, specifically engineered for robust document intelligence tasks. With 689 million parameters, it excels in optical character recognition (OCR), layout analysis, and table recognition, offering significant improvements over previous versions.

Read More

The model demonstrates exceptional accuracy, scoring 85.9 on OmniParseBench and 83.7% on olmOCR-bench, making it the highest-scoring open model under 1 billion parameters in Datalab's evaluations. It boasts impressive speed, achieving a throughput of 4.5 pages per second on an H100 GPU at 192 DPI, which is 1.7 times faster than Surya 2 with MTP.

Surya OCR 2.5 is highly multilingual, achieving a 74.9% pass rate on an internal benchmark covering 91 languages. It performs comprehensive layout analysis, identifying elements such as tables, images, and headers, and accurately determines reading order. A key feature is its ability to output tables as HTML, complete with merged cells represented by `colspan` and `rowspan` attributes.

Beyond full-page OCR, Surya OCR 2.5 also includes smaller, specialized models for line-level text detection and OCR error detection. It supports a wide range of document types, from newspapers and reference books to government forms, handwritten letters, and corporate documents. The model can be installed and run with inference backends like vllm (for NVIDIA GPUs) or llama.cpp (for CPU/Apple Silicon), and an interactive Streamlit app is available for easy testing.

Commercial usage of the Surya code is licensed under Apache 2.0, while the model weights use a modified AI Pubs Open Rail-M license, allowing free use for research, personal projects, and startups under $5M funding/revenue. Broader commercial licensing options are available through Datalab's pricing page. Datalab also offers a managed platform that runs Surya and its higher-accuracy variant, Chandra, with free credits for new sign-ups.

  • CategoryComputer Vision Tools
  • Pricing ModelFreemium
  • DeploymentCloud
  • PlatformsWeb

  • Image-Text-to-Text Model: Processes images to extract text and structural information.

  • High Accuracy: Scores 85.9 on OmniParseBench and 83.7% on olmOCR-bench.

  • Fast Throughput: Achieves 4.5 pages/s on H100 at 192 DPI.

  • Multilingual Support: Benchmarked across 91 languages with 74.9% overall pass rate.

  • Layout Analysis: Detects tables, images, headers, and determines reading order.

  • Table Recognition: Extracts tables as HTML with merged cells (colspan/rowspan).

  • Text Line Detection: Separate model for precise line-level text detection.

  • OCR Error Detection: Dedicated model for identifying OCR inaccuracies.

  • VLM Integration: Runs layout, OCR, and table recognition through a single VLM.

  • Flexible Inference Backends: Supports vllm (NVIDIA GPU) and llama.cpp (CPU/Apple Silicon).

  • Interactive Streamlit App: Provides an interactive interface for testing images and PDFs.

  • Customizable Settings: Override settings via environment variables for fine-tuning.

  • Commercial Licensing: Apache 2.0 for code, modified Open Rail-M for model weights.

  • Managed Platform Access: Available on Datalab's managed platform with free credits.

  • Math/Equation Handling: Recognizes and outputs mathematical equations in KaTeX-compatible LaTeX within HTML.

  1. Install Surya OCR: Install the `surya-ocr` package using pip.

  2. Set up Inference Backend: Configure either vllm (for NVIDIA GPU) or llama.cpp (for CPU/Apple Silicon) as the inference server.

  3. Run OCR Command: Execute the OCR command with your image or PDF path to extract text and bounding boxes.

  4. Perform Layout Analysis: Use the layout command to detect document structure and reading order.

  5. Extract Tables: Utilize the table recognition command to get tables as HTML output.

  6. Process Text Line Detection: Run the text line detection command to identify individual text lines.

  7. Integrate via Python: Access Surya OCR functionalities directly from Python scripts.

  8. Use Interactive App: Launch the Streamlit app to interactively test Surya on images or PDF files.

  • Document Digitization
  • Data Extraction
  • Content Archiving
  • Multilingual Document Processing
  • Layout Understanding
  • Automated Form Processing
  • Research and Academia
  • Business Process Automation

Surya OCR 2.5 Reviews

Loading...

Popular AI Tools Like Surya OCR 2.5

GOT-OCR2.0 is an advanced OCR model designed for efficient text recognition. It leverages a unified end-to-end approach to improve accuracy and performance, making it ideal for…

AI Models & LLMs
View Tool

Advanced OCR model designed for efficient text recognition. It leverages a unified end-to-end approach to improve accuracy and performance, making it ideal for…GOT-OCR2.0 is an advanced OCR model designed for efficient text recognition. It leverages a unified end-to-end approach to improve accuracy and performance, making it ideal for…

AI Models & LLMs
See the Top 5 AI Models

MiniCPM-OCR 1.0 is an OCR-specific model designed for text-centric document understanding. It excels in parsing text, tables, and charts, offering efficient inference and easy…

AI Models & LLMs
View Tool

OCR-specific model designed for text-centric document understanding. It excels in parsing text, tables, and charts, offering efficient inference and easy…MiniCPM-OCR 1.0 is an OCR-specific model designed for text-centric document understanding. It excels in parsing text, tables, and charts, offering efficient inference and easy…

AI Models & LLMs
See the Top 5 AI Models

LightOnOCR-3-4B is a high-performance OCR model offering advanced layout and visual understanding capabilities. It provides accurate transcription and bounding box coordinates for…

AI Models & LLMs
View Tool

High-performance OCR model offering advanced layout and visual understanding capabilities. It provides accurate transcription and bounding box coordinates for…LightOnOCR-3-4B is a high-performance OCR model offering advanced layout and visual understanding capabilities. It provides accurate transcription and bounding box coordinates for…

AI Models & LLMs
See the Top 5 AI Models

OCR - Image Reader

Browser Plugins

This Chrome extension captures and converts images to text using an internal OCR engine. It supports over 100 languages, automatic orientation, and script detection. The tool…

Computer Vision Tools
View Tool

Browser Plugins

This Chrome extension captures and converts images to text using an internal OCR engine. It supports over 100 languages, automatic orientation, and script detection. The tool…

Computer Vision Tools
See the Top 250 Browser Plugins

Tesseract OCR

AI GitHub Repos

Tesseract OCR is an open-source optical character recognition engine. It supports multiple languages and can be used for text extraction from images. Ideal for developers seeking…

Computer Vision Tools
View Tool

AI GitHub Repos

Open-source optical character recognition engine. It supports multiple languages and can be used for text extraction from images. Ideal for developers seeking…Tesseract OCR is an open-source optical character recognition engine. It supports multiple languages and can be used for text extraction from images. Ideal for developers seeking…

Computer Vision Tools
See the Top 250 AI GitHub Repos

RolmOCR

AI Models

RolmOCR by Reducto AI is an open-source OCR tool that offers faster processing and lower memory usage compared to its predecessor, olmOCR. It is designed to handle various…

AI Models & LLMs
View Tool

AI Models

RolmOCR by Reducto AI is an open-source OCR tool that offers faster processing and lower memory usage compared to its predecessor, olmOCR. It is designed to handle various…

AI Models & LLMs
See the Top 5 AI Models

Surya OCR

AI GitHub Repos

Surya OCR is a versatile tool for optical character recognition, layout analysis, reading order, and table recognition across 90+ languages. It is designed to enhance document…

AI Document & PDF Tools

Ranked #96 in AI GitHub Repos

View Tool

AI GitHub Repos

Versatile tool for optical character recognition, layout analysis, reading order, and table recognition across 90+ languages. It is designed to enhance document…Surya OCR is a versatile tool for optical character recognition, layout analysis, reading order, and table recognition across 90+ languages. It is designed to enhance document…

AI Document & PDF Tools
Ranked #96 in AI GitHub Repos

PaddleOCR

AI GitHub Repos

PaddleOCR is a powerful, lightweight OCR toolkit designed to convert PDFs and image documents into structured data for AI applications. It supports over 100 languages and bridges…

Computer Vision Tools

Ranked #12 in AI GitHub Repos

View Tool

AI GitHub Repos

Powerful, lightweight OCR toolkit designed to convert PDFs and image documents into structured data for AI applications. It supports over 100 languages and bridges…PaddleOCR is a powerful, lightweight OCR toolkit designed to convert PDFs and image documents into structured data for AI applications. It supports over 100 languages and bridges…

Computer Vision Tools
Ranked #12 in AI GitHub Repos
1 of 8