README.md

---
base_model:
- UBC-NLP/AraT5v2-base-1024
language:
- ar
library_name: transformers
license: apache-2.0
metrics:
- bleu
pipeline_tag: translation
tags:
- Syrian
- Shami
- MT
- MSA
- Dialect
- ArabicNLP
---

# SHAMI-MT-2MSA : A Machine Translation Model From Syrian Dialect to MSA

This model is part of the work presented in the paper [SHAMI-MT: A Syrian Arabic Dialect to Modern Standard Arabic Bidirectional Machine Translation System](https://huggingface.co/papers/2508.02268).

## Paper Abstract

The rich linguistic landscape of the Arab world is characterized by a significant gap between Modern Standard Arabic (MSA), the language of formal communication, and the diverse regional dialects used in everyday life. This diglossia presents a formidable challenge for natural language processing, particularly machine translation. This paper introduces \textbf{SHAMI-MT}, a bidirectional machine translation system specifically engineered to bridge the communication gap between MSA and the Syrian dialect. We present two specialized models, one for MSA-to-Shami and another for Shami-to-MSA translation, both built upon the state-of-the-art AraT5v2-base-1024 architecture. The models were fine-tuned on the comprehensive Nabra dataset and rigorously evaluated on unseen data from the MADAR corpus. Our MSA-to-Shami model achieved an outstanding average quality score of \textbf{4.01 out of 5.0} when judged by OPENAI model GPT-4.1, demonstrating its ability to produce translations that are not only accurate but also dialectally authentic. This work provides a crucial, high-fidelity tool for a previously underserved language pair, advancing the field of dialectal Arabic translation and offering significant applications in content localization, cultural heritage, and intercultural communication.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/628f7a71dd993507cfcbe587/_w3yOhX5YjaMB4Jc_mrib.png)

## Model Description

SHAMI-MT-2MSA is one of two specialized models that constitute the **SHAMI-MT** bidirectional machine translation system. This particular model is designed to translate from **Syrian dialect to Modern Standard Arabic (MSA)**. Built on the robust AraT5v2-base-1024 architecture, this model bridges the gap between formal Arabic and the rich dialectal variations of Syrian Arabic.

## Usage

This model can be used directly with the Hugging Face `transformers` library.

```python
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

# Load tokenizer and model
model_id = "Omartificial-Intelligence-Space/Shami-MT-2MSA"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSeq2SeqLM.from_pretrained(model_id)

# Example input: Syrian Arabic dialect
input_text = "كيفك اليوم؟" # "How are you today?" in Syrian dialect
inputs = tokenizer(input_text, return_tensors="pt")

# Generate translation
outputs = model.generate(**inputs, max_new_tokens=128) # Added max_new_tokens for generation to prevent infinite loop
translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)

print(f"Syrian Dialect: {input_text}")
print(f"Modern Standard Arabic: {translated_text}")
```

## Citation

If you use this model in your research, please cite the main paper and the dataset paper:

```bibtex
@article{sibaee2025shamimt,
  title={SHAMI-MT: A Syrian Arabic Dialect to Modern Standard Arabic Bidirectional Machine Translation System},
  author={Sibaee, Serry and Nacar, Omer},
  year={2025},
  journal={Hugging Face Papers},
  url={https://huggingface.co/papers/2508.02268}
}

@article{nayouf2023nabra,
  title={Nâbra: Syrian Arabic dialects with morphological annotations},
  author={Nayouf, Amal and Hammouda, Tymaa Hasanain and Jarrar, Mustafa and Zaraket, Fadi A and Kurdy, Mohamad-Bassam},
  journal={arXiv preprint arXiv:2310.17315},
  year={2023}
}
```

## Contact & Support

For questions, issues, or contributions, please visit the [model repository](https://huggingface.co/Omartificial-Intelligence-Space/Shami-MT-2MSA) or contact the development team.