paddleocr-text-recognition
paddlepaddle598 installs
Turn images and scanned PDFs into exact text.
What it does
Extracts machine-readable text from images and scanned PDFs, with line-level results and optional bounding-box coordinates.
When to use it
Use for extracting text from images or PDFs when line-level or box-level text is the goal.
How to use it
Give it an image or PDF, supplied locally or by URL; it returns the extracted text in the conversation.
What you provide
- Your files
Uses
PA
Latest review
What you need · 2
Requires the paddleocr CLI to call the OCR API.
Requires PADDLEOCR_ACCESS_TOKEN as an environment variable for API authentication.
Access · 1
This skill
PaddleOCR
Write
Sends documents to PaddleOCR