paddleocr-text-recognition
aidenwu02094k installs
Turn images and scanned PDFs into plain text.
What it does
Extracts readable text from images and scanned PDFs using PaddleOCR, with line-level recognition and optional bounding boxes.
When to use it
Use for extracting text from images or PDFs when line-level text is wanted rather than tables, formulas, or full document layout.
How to use it
Give it an image or PDF, locally or by URL; it returns the recognized text and the path to saved raw JSON.
What you provide
- Your files
Uses
PA
Latest review
What you need · 3
Requires Python 3.9 or later.
Requires uv to run the bundled scripts and automatically resolve their inline dependencies.
Access · 2
This skill
PaddleOCR
Write
Sends images to PaddleOCR
httpx
Execute
Installs the HTTPX dependency