GOT-OCR

General OCR Theory model with unified end-to-end architecture for various OCR tasks.

Open SourceSelf HostedOffline CapableGPU Required (6GB+ VRAM)
0.0 (0)

About

GOT-OCR, General OCR Theory by StepFun, is a unified end-to-end model that reads scene text, document text, formulas, charts, sheet music, and more through a single vision-encoder-decoder architecture rather than separate task-specific systems. It supports multi-page and region-based recognition and is positioned as a step toward OCR 2.0. Released under the Apache 2.0 license.

Reviews (0)

Leave a Review

No reviews yet. Be the first to review!

Details

Price
Free
Platform
Local/Desktop
Difficulty
Intermediate (3/5)
License
Apache-2.0
Minimum VRAM
6 GB
Added
Apr 3, 2026

Related Tools

Python library for extracting text, tables, and metadata from PDFs.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

Python bindings for MuPDF library for fast PDF text and image extraction.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

Python library for extracting tables from PDF files.

Open SourceSelf HostedOffline
Beginner
0.0 (0)
Featured

Ready-to-use OCR library supporting 80+ languages with simple Python API.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

Turn-key OCR system for historical and non-Latin script documents.

Open SourceSelf HostedOffline
Intermediate
0.0 (0)

Vision-language model based OCR toolkit by AI2 for document understanding.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)
Browse all OCR & Document Processing tools