Update README.md

README.md

@@ -65,19 +65,14 @@ It will likely make more sense to use this model in the context of a 'human in t
 You can use cURL to access this model:
 
 ```
-$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/davanstrien/autotrain-cultural_heritage_metadata_accuracy-48840118272
+$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "Elemento di decorazione architettonica a rilievo"}' https://api-inference.huggingface.co/models/davanstrien/autotrain-cultural_heritage_metadata_accuracy-48840118272
 ```
 
-Or Python API:
+You can also use the model locally be leveraging a Transformers [pipeline](https://huggingface.co/docs/transformers/pipeline_tutorial)
 
 ```
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from transformers import pipeline
 
-model = AutoModelForSequenceClassification.from_pretrained("davanstrien/autotrain-cultural_heritage_metadata_accuracy-48840118272", use_auth_token=True)
-
-tokenizer = AutoTokenizer.from_pretrained("davanstrien/autotrain-cultural_heritage_metadata_accuracy-48840118272", use_auth_token=True)
-
-inputs = tokenizer("I love AutoTrain", return_tensors="pt")
-
-outputs = model(**inputs)
+pipe = pipeline('text-classification', model='biglam/cultural_heritage_metadata_accuracy')
+pipe("Elemento di decorazione architettonica a rilievo")
 ```