The Usage of tokenizer for Myanmar is same as Laos in https://github.com/GKLMIP/Pretrained-Models-For-Laos.
If you use our model, please consider citing our paper:
@InProceedings{,
author="Jiang, Shengyi
and Huang, Xiuwen
and Cai, Xiaonan
and Lin, Nankai",
title="Pre-trained Models and Evaluation Data for the Myanmar Language",
booktitle="The 28th International Conference on Neural Information Processing",
year="2021",
publisher="Springer International Publishing",
address="Cham",
}