{% extends "base.html" %} {% block title %}ArtificeOCR — About{% endblock %} {% block content %}
Local-first · offline OCR, cleanup & translation

About ArtificeOCR

ArtificeOCR is a Tropy-first workbench for turning selected document pages into corrected, searchable text without sending a page to a remote service. Choose individual pages from a read-only Tropy project, run them through local OCR, review the results, then return selected text to the same Tropy project as notes or transcriptions. Files outside Tropy remain available as a secondary source.

Pipeline stages

  1. OCR — reads each page image with a vision-capable model served locally by either Ollama or LM Studio. Both routes are release-gated end to end; Hugging Face and cloud-compatible APIs remain optional alternatives.
  2. Cleanup — a language model pass corrects recognition errors and normalises layout while a content-preservation guard keeps the original wording whenever the edit looks lossy, so a page is either cleaned or left untouched, never silently reworded.
  3. Title — generates a concise title for each page when the option is enabled.
  4. Translate — renders the cleaned text into English. A confident language-detection pass skips already-English pages rather than risking an LLM "helpfully" rewriting text that didn't need translating.
  5. Export — compile any stage's output into a continuous reading PDF or Markdown file, or send corrected text back to Tropy as notes or transcriptions.

Preview, history and correction

The Preview tab shows the source scan beside raw OCR, cleaned and translated text side by side, with the original always one click away behind "Original" so a correction never hides what the model actually produced. History keeps every past run and document searchable, with the same compare view and a thumbnail strip across the source images. Batch Correct applies a single find/replace across the whole queue or an explicit selection.

Quick actions

Ctrl+K (Cmd+K on macOS) opens a command palette that jumps to any tab or runs a queue action without leaving the keyboard. The same palette also toggles light and dark themes, as does the icon at the right of the top navigation bar.

Design language

This interface implements The New Masses design system: an offline-first, print-inflected editorial aesthetic with warm paper surfaces, a deep teal accent, and fluid serif typography. All design tokens are served from the shared packages/shared-ui/shared_ui/assets/tokens.css; never hardcode colours or spacing.

Run it

From the project root: 

pip install -e ".[web]"
artifice-ocr-web
# → http://localhost:8765

ArtificeOCR · an Artifice platform · FastAPI + Jinja2 · vanilla JS.

{% endblock %}