README.md

metadata

license: cc-by-nc-4.0
datasets:
  - guymorlan/levanti
language:
  - ar
  - en
pipeline_tag: translation
widget:
  - text: P I wanna go to the store tomorrow

Levanti (English -> colloquial Levantine Arabic) translator

Trained on the Levanti dataset by fine-tuning Helsinki-NLP/opus-mt-en-ar for 8 epochs. This model is trained to support dialect conditional generation by utilizing the first token (followed by a space) as an indicator of the desired dialect:

• P for Palestinian
• L for Lebanese
• S for Syrian
• E for Egyptian

Example usage

from transformers import pipeline
trans = pipeline("translation", "guymorlan/levanti_translate_en_ar")
trans("P I wanna go to the store tomorrow")

Out[1]: [{'translation_text': 'بدي أروح ع الدكان بكرا'}]

Attribution

Created by Guy Mor-Lan.
Contact: guy.mor AT mail.huji.ac.il