shreeshrii Goto Github PK

hindi-hunspell

Hindi wordlists, dictionary and affix files in hunspell format

imagesbih

Images and ground truth for Bihari Languages for OCR evaluation

imageshin

Images and Ground Truth files in Hindi for OCR evaluation

imageskan

Tesseract OCR 4.0.0 test tutorial

imagesmar

Images and groundtruth text for Marathi for OCR evaluation

imagessan

Images and groundtruth text for Sanskrit for OCR evaluation

keyboards

Open Source Keyman keyboards

kraken_devanagari

Kraken models for Devanagari

kraken_grantha

line images and their ground truth in grantha script

langdata_lstm

Data used for LSTM model training

ocr-evaluation-tools

sanscript.js

Transliteration package for Indian scripts

sanscript.php

Transliteration package for Indian scripts

shreeshrii.github.io

tess4tutorial

Training Data files for https://github.com/Shreeshrii/tess4training - eng_layer_eng

tess5train-fonts

Files and Scripts to run Tesseract 5 LSTM Training using fonts

tess5training-rajarajan

tessdata

Tessdata 3.0x zipped files for Hindi and Arabic (DO NOT DELETE)

tessdata_arabic

Finetuned traineddata files for Arabic

tessdata_brahmi

traineddata for Brahmi script for Tesseract 4

tessdata_coptic

Traineddata files for Tesseract 4.0.0 for Coptic OCR

tessdata_emoji

Traineddata for recognizing emoji icons with Tesseract 4

tessdata_jav_java

Tesseract 4.0.0 training data for Javanese Script (Aksara Jawa)

tessdata_micr

MICR traineddata - legacy model for Tesseract 4.0x

tessdata_ocrb

tesseract 4 traineddata for MRZ using OCR-B fonts

tessdata_shreetest

finetuned traineddata files for tesseract 4.0.0 for testing

tessdata_ssd

Tesseract 4 traineddata for recognizing Seven Segment Display

tessdata_stylus

Finetuned traineddata for Uppercase English in Stylus fonts

tessdata_tagalog

Tesseract4 training data for Tagalog / Baybayin script

tessdata_tamil

Tamil traineddata for testing