Unlimited OCR: One-shot long-horizon parsing

2026-06-23 | original

read original more articles

Why This Matters

Unlimited OCR introduces a groundbreaking approach to long-horizon parsing, enabling more accurate and efficient text extraction from complex and multi-page documents. This advancement has the potential to significantly enhance automation, data extraction, and digital document processing across various industries.

Key Takeaways

Supports multi-page and PDF parsing for comprehensive document analysis
Utilizes transformer models optimized for NVIDIA GPUs for high performance
Enables long-horizon parsing with extended context windows up to 32,768 tokens

Unlimited OCR Works

Welcome the Era of One-shot Long-horizon Parsing.

Release

[2026/06/23] 📄 Our paper is now available on arXiv.

[2026/06/23] 🤝 Thanks to the ModelScope community for their support. Our model is now available at ModelScope.

[2026/06/22] 🚀 We present Unlimited-OCR, aiming to push Deepseek-OCR one step further.

Inference

Transformers

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.3 + CUDA12.9：

torch==2.10.0 torchvision==0.25.0 transformers==4.57.1 Pillow==12.1.1 matplotlib==3.10.8 einops==0.8.2 addict==2.4.0 easydict==1.13 pymupdf==1.27.2.2 psutil==7.2.2

... continue reading

Explore topics: unlimited-ocr modelscope huggingface transformers nvidia gpus baidu