Views
No views yet
mBART-50 model that translates Algerian Darija written in Latin script into Darija written in Arabic script — handling French/English loanwords, telecom-specific vocabulary, and multiple real-world spelling variations of the same word.1from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
2
3tokenizer = AutoTokenizer.from_pretrained("Chaima-KHENAFIF/darija-latin-to-arabic-translator")
4model = AutoModelForSeq2SeqLM.from_pretrained("Chaima-KHENAFIF/darija-latin-to-arabic-translator")
5
6inputs = tokenizer("3andi offre tae 300DA w cnx lente", return_tensors="pt")
7output = model.generate(**inputs, max_length=50)
8print(tokenizer.decode(output[0], skip_special_tokens=True))te3i / ta3i / te'i / taai) map to the same correct Arabic output.| Metric | Score |
|---|---|
| BLEU | 0.83 |