ocr-super-surya

Community

GPU OCR with Surya for multi-language text.

Authoraktsmm
Version1.0.0
Installs0

System Documentation

What problem does it solve?

OCR Super Surya streamlines text extraction from images and PDFs by leveraging Surya's GPU-accelerated OCR, enabling fast, accurate digitization of documents.

Core Features & Use Cases

  • High accuracy: ~2x accuracy over traditional OCR tools across 90+ languages, including Japanese.
  • GPU-accelerated processing: PyTorch/CUDA optimized for large batches and high-resolution images.
  • Multi-format support: Works on images, PDFs, and mixed documents with embedded text.
  • Use Case: Convert scanned invoices or product catalogs into searchable text and structured data for analytics.

Quick Start

Install surya-ocr and dependencies, then run ocr_image, ocr_pdf, or ocr_batch on your documents. Example: ocr_image('invoice.png') or ocr_pdf('report.pdf').

Dependency Matrix

Required Modules

torchPillowsuryapypdfium2

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ocr-super-surya
Download link: https://github.com/aktsmm/Agent-Skills/archive/main.zip#ocr-super-surya

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.