Churro OCR Documentation#

Churro OCR is a Python 3.12+ OCR toolkit for historical document transcription. The docs start with a CLI-first local workflow, then branch into task guides and deeper reference material.

Quick Start#

uv tool install churro-ocr
churro-ocr install hf
churro-ocr transcribe \
  --image scan.png \
  --backend hf \
  --model stanford-oval/churro-3B

Use Getting Started for the full setup flow and first-run guidance.

Start Here#

Getting Started

Install the CLI, install the first runtime, and verify one successful OCR run.

Getting Started

Common Tasks#

CLI

Run transcribe, extract-pages, and runtime installs from the shell.

CLI
OCR Workflows

Choose the right Python workflow for single-page images, PDFs, and photographed spreads.

OCR Workflows
Page Detection

Extract page crops without OCR, or choose a detector backend for layout discovery.

Page Detection
Providers And Configuration

Choose a backend, install its runtime, and see minimal provider setup examples.

Providers And Configuration

Learn More#