ocr

Generated Handwriting

You can check generate-handwriting.ipynb on how to generate Malay handwriting.

Dataset is simple, malay label can get from the name syarif.png.

alt text

download

1. Download dataset from https://f000.backblazeb2.com/file/malay-dataset/jawi-rumi.tar.gz

2. Download train-test-rumi-to-jawi.json

Citation

@misc{Malay-Dataset, We gather Bahasa Malaysia corpus!, Generated Handwriting Dataset,
author = {Husein, Zolkepli},
title = {Malay-Dataset},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/huseinzol05/malay-dataset/tree/master/ocr/handwriting}}
}

Malay-to-Jawi

You can check rumi-to-jawi-to-image.ipynb on how to generate Malay to Jawi.

Dataset is simple, malay label can get from the name idola.png.

download

1. Download dataset from https://f000.backblazeb2.com/file/malay-dataset/jawi-rumi.tar.gz

2. Download train-test-rumi-to-jawi.json

Citation

@misc{Malay-Dataset, We gather Bahasa Malaysia corpus!, Malay-to-Jawi Dataset,
author = {Husein, Zolkepli},
title = {Malay-Dataset},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/huseinzol05/malay-dataset/tree/master/normalization/stemmer}}
}