This is part of an ongoing research about Moroccan dialect (Darija) and this is a simple translitera
A Transformer translitertion model to convert Moroccan Darija text written in Arabizi (Latin script)
The Moroccan Darija Wiki Dataset consists of 10,044 parallel text samples of Moroccan Darija sourced
The Moroccan Darija Wiki Audio Dataset consists of 551 parallel text and speech samples of Moroccan
Training and data analysis code for Al-Atlas dataset and models # Al-Atlas: Data, Models, Evals ##