metadata

language:
  - en
  - ar
tags:
  - translation
  - Arabic Abjad Characters
license: Apache 2.0
datasets:
  - marefa-mt

Marefa-Mt-En-Ar

Model description

This is a model for translating English to Arabic. The special about this model that is take into considration the using of additional Arabic characters like پ or گ.

Intended uses & limitations

How to use

from transformers import MarianTokenizer, MarianMTModel
mname = "marefa-nlp/marefa-mt-en-ar"
tokenizer = MarianTokenizer.from_pretrained(mname)
model = MarianMTModel.from_pretrained(mname)

input = "Hello, I am here."

translated_tokens = custom_model.generate(**tokenizer.prepare_seq2seq_batch([input], return_tensors="pt"))
translated_text = [tokenizer.decode(t, skip_special_tokens=True) for t in translated_tokens]

print(translated_text) # أهلا. أنا هنا