Update README
Browse files
README.md
CHANGED
|
@@ -5,21 +5,39 @@ language:
|
|
| 5 |
tags:
|
| 6 |
- translation
|
| 7 |
- Arabic Abjad Characters
|
|
|
|
| 8 |
license: Apache 2.0
|
| 9 |
datasets:
|
| 10 |
- marefa-mt
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# Marefa-Mt-En-Ar
|
|
|
|
| 14 |
|
| 15 |
## Model description
|
| 16 |
|
| 17 |
This is a model for translating English to Arabic. The special about this model that is take into considration the
|
| 18 |
using of additional Arabic characters like `پ` or `گ`.
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
## Intended uses & limitations
|
| 21 |
|
| 22 |
-
#### How to use
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
```python
|
| 25 |
from transformers import MarianTokenizer, MarianMTModel
|
|
@@ -27,10 +45,13 @@ mname = "marefa-nlp/marefa-mt-en-ar"
|
|
| 27 |
tokenizer = MarianTokenizer.from_pretrained(mname)
|
| 28 |
model = MarianMTModel.from_pretrained(mname)
|
| 29 |
|
| 30 |
-
|
|
|
|
| 31 |
|
| 32 |
-
translated_tokens =
|
| 33 |
translated_text = [tokenizer.decode(t, skip_special_tokens=True) for t in translated_tokens]
|
| 34 |
|
| 35 |
-
|
|
|
|
|
|
|
| 36 |
```
|
|
|
|
| 5 |
tags:
|
| 6 |
- translation
|
| 7 |
- Arabic Abjad Characters
|
| 8 |
+
- Arabic
|
| 9 |
license: Apache 2.0
|
| 10 |
datasets:
|
| 11 |
- marefa-mt
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# Marefa-Mt-En-Ar
|
| 15 |
+
# نموذج المعرفة للترجمة الآلية من الإنجليزية للعربية
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
| 19 |
This is a model for translating English to Arabic. The special about this model that is take into considration the
|
| 20 |
using of additional Arabic characters like `پ` or `گ`.
|
| 21 |
|
| 22 |
+
## عن النموذج
|
| 23 |
+
هذا النموذج للترجمة الآلية من اللغة الإنجليزية إلى اللغة العربية, هو أول نماذج الترجمة الآلية التي تصدر تحت رعاية
|
| 24 |
+
[موسوعة المعرفة](https://www.marefa.org)
|
| 25 |
+
يتميز هذا النموذج عن غيره من النماذج بدعمه لحروف الأبجدية العربية الإضافية لتمميز الصوتيات الخاصة في اللغة الإنجليزية مثل `پ` , `گ`.
|
| 26 |
+
|
| 27 |
+
يمكنك زيارة
|
| 28 |
+
[هذه الصفحة](https://www.marefa.org/%D8%A7%D9%84%D9%85%D8%B9%D8%B1%D9%81%D8%A9:%D8%AF%D9%84%D9%8A%D9%84_%D8%A7%D9%84%D8%A3%D8%B3%D9%84%D9%88%D8%A8#.D8.AD.D8.B1.D9.88.D9.81_.D8.A5.D8.B6.D8.A7.D9.81.D9.8A.D8.A9_.D9.84.D9.84.D9.86.D8.B7.D9.82_.D8.A7.D9.84.D8.B3.D9.84.D9.8A.D9.85)
|
| 29 |
+
لمعرفة أكثر عن أسلوب إستخدام هذه الحروف الأبجدية العربية
|
| 30 |
## Intended uses & limitations
|
| 31 |
|
| 32 |
+
#### How to use كيفية الإستخدام
|
| 33 |
+
|
| 34 |
+
Install transformers and sentencepiece
|
| 35 |
+
|
| 36 |
+
`$ pip3 install transformers==4.3.0 sentencepiece==0.1.95`
|
| 37 |
+
|
| 38 |
+
> If you are using `Google Colab`, please restart your runtime after installing the packages.
|
| 39 |
+
|
| 40 |
+
-----------
|
| 41 |
|
| 42 |
```python
|
| 43 |
from transformers import MarianTokenizer, MarianMTModel
|
|
|
|
| 45 |
tokenizer = MarianTokenizer.from_pretrained(mname)
|
| 46 |
model = MarianMTModel.from_pretrained(mname)
|
| 47 |
|
| 48 |
+
# English Sample Text
|
| 49 |
+
input = "President Putin went to the presidential palace in the capital, Kiev"
|
| 50 |
|
| 51 |
+
translated_tokens = model.generate(**tokenizer.prepare_seq2seq_batch([input], return_tensors="pt"))
|
| 52 |
translated_text = [tokenizer.decode(t, skip_special_tokens=True) for t in translated_tokens]
|
| 53 |
|
| 54 |
+
# translated Arabic Text
|
| 55 |
+
print(translated_text)
|
| 56 |
+
# ذهب الرئيس پوتن إلى القصر الرئاسي في العاصمة كييڤ
|
| 57 |
```
|