TEI Pipeline Model loading...

OCR text extraction and TEI P5 XML markup from historical document images.

1 Upload & Configure

📄

Drop an image or PDF here, or click to browse

Supports PDF, JPEG, PNG, TIFF, BMP

Genre: Model:

Language:

Custom Tags (advanced)

Define additional elements for the model to tag. They will be included as <seg type="..."> in the TEI output.

2 Processing

Waiting...

3 Confirm Metadata

These values were inferred from the document. Edit as needed, then click Apply to update the TEI header.

Title:

Author:

Date:

Publisher:

Place:

Language:

4 Output

XML Preview

Validation