Update README.md

README.md

@@ -47,17 +47,10 @@ Overview of corpus statistics. %noisy gives the percentage of agency mentions wi
 You can use this model with Transformers *pipeline* for NER.
 
 ```python
-from transformers import AutoTokenizer, AutoModelForTokenClassification
 from transformers import pipeline
 
-tokenizer = AutoTokenizer.from_pretrained("impresso-project/bert-newsagency-ner-fr")
-model = AutoModelForTokenClassification.from_pretrained("impresso-project/bert-newsagency-ner-fr")
-
-nlp = pipeline("newsagency-ner", model=model, tokenizer=tokenizer, trust_remote_code=True)
-example = "Mon nom est François et j'habite à Paris. (AFP)"
-
-ner_results = nlp(example)
-print(ner_results)
+nlp = pipeline("newsagency-ner", model="impresso-project/bert-newsagency-ner-fr", trust_remote_code=True)
+nlp("Mon nom est François et j'habite à Paris. (Reuter)")
 ```
 
 ### BibTeX entry and citation info