FICHA · MANJARO

tesseract-data-srp_latn

Tesseract OCR data (srp_latn)

  • Data
  • DATA
  • OCR
  • LOCALIZATION
  • Dependency only
official+codex · reviewed · May 29, 2026 description in en

Description

Enables Tesseract to recognize Serbian text written in the Latin script. It is useful when Serbian documents use Latin letters rather than Cyrillic and need searchable or editable OCR output.

Use this model for Serbian Latin sources. Wrong script selection can silently reduce accuracy, especially for names and formal records.

Permissions

Permissions not analysed for this source yet.