grabar-ocr

andylitalo/grabar-ocr

Manages pipeline to digitize "Grabar" (Classical Armenian) texts

Python Stars: 1 Forks: 0 Language/NLP
ocrclassical-armeniantext-digitizationgrabarpipeline

Summary

This is a partially implemented Classical Armenian (Grabar) text digitization project. The README describes an ambitious cloud-native pipeline (Airflow, k3s, TrOCR, PostgreSQL) but the repository reveals a simpler local implementation. The actual working pipeline uses Tesseract OCR followed by Gemini AI for correction and translation, processing a corpus of a scanned book (pages 458-641). The cloud infrastructure directories are stubs.

View on GitHub
More in: Armenian Language NLP Tools →

Similar Projects

Mashtots-OCR
GevorgGevorgyan1/Mashtots-OCR

An OCR project for Armenian handwritten text using the Mashtots dataset, implemented in TensorFlow/Keras and trained ...

Jupyter Notebook Stars: 0
armenian-ocr-toolkit
Serge-Ordanyan/armenian-ocr-toolkit

A Python toolkit for performing OCR on Armenian historical documents. It uses pytesseract with multiple preprocessing...

Python Stars: 0
arm2txt
antranigv/arm2txt

A web application for Armenian OCR (Optical Character Recognition) built with Elixir and Phoenix. It extracts Armenia...

Elixir Stars: 9
greekOCR
kkkamur07/greekOCR

Nomicous is an open-source platform for AI-assisted transcription, annotation, and text extraction of historical manu...

Python Stars: 7
armenian-ocr
Edi-Gevorgyan/armenian-ocr

A Java library that uses Google Cloud Vision API to extract Armenian text from images and saves the output to a .docx...

Java Stars: 0
Preserving-the-past-with-AI
Aren-AiKing/Preserving-the-past-with-AI

An AI-powered system for analyzing scanned Armenian newspapers using computer vision (YOLO for section detection, Ope...

Python Stars: 0