This model is finetuned on Helsinki-NLP/opus-mt-tc-big-en-ar for English to Egyptian dialect translations. It was trained on more than 150,000 rows with more than 10 Million tokens

Usage

python

from transformers import pipeline

modelName = "NAMAA-Space/masrawy-english-to-egyptian-arabic-translator-v2.9"
translator = pipeline("translation", model=modelName)
output = translator("Where is the nearest pharmacy")

print(output[0]['translation_text'])

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 8

Framework versions

Transformers 4.35.2
Pytorch 2.1.1+cu121
Datasets 2.14.5
Tokenizers 0.15.1

Benchmarks

This model ranks second after openai/gpt-4o in Egyptian translation leaderboard

Citation


If you use NAMAA-Space/masrawy-english-to-egyptian-arabic-translator-v2.9, please cite it as follows:

@article{namaa_01_2025,
    title={Masrawy English to Egyptian Translator},
    url={https://huggingface.co/NAMAA-Space/masrawy-english-to-egyptian-arabic-translator-v2.9},
    publisher={NAMAA},
    author={NAMAA Team},
    year={2025}
}