Update usage to work with latest `transformers`

README.md

@@ -21,7 +21,7 @@ model_name = "QCRI/bert-base-multilingual-cased-pos-english"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForTokenClassification.from_pretrained(model_name)
 
-pipeline = TokenClassificationPipeline(model, tokenizer)
+pipeline = TokenClassificationPipeline(model=model, tokenizer=tokenizer)
 outputs = pipeline("A test example")
 print(outputs)
 ```