Update README.md

README.md

@@ -80,12 +80,13 @@ It is recommended to apply our preprocessing function before training/testing on
 **Install farasapy to segment text for AraBERT v1 & v2 `pip install farasapy`**
 
 ```python
-from arabert.preprocess import preprocess
+from arabert.preprocess import ArabertPreprocessor
+
+model_name="bert-large-arabertv02"
+arabert_prep = ArabertPreprocessor(model_name=model_name)
 
 text = "ولن نبالغ إذا قلنا إن هاتف أو كمبيوتر المكتب في زمننا هذا ضروري"
-preprocess(text,
-    model_name="bert-large-arabertv02",
-    keep_emojis=False)
+arabert_prep.preprocess(text)
 ```
 
 ## Accepted_models