Update app.py

app.py

@@ -1,27 +1,24 @@
 from transformers import pipeline
 import gradio as gr
 
-# Use a pipeline as a high-level helper
-
+# Initialize the pipeline
 pipe = pipeline("text-classification", model="ZachBeesley/Spam-Detector")
 
-# Load model directly
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-
-tokenizer = AutoTokenizer.from_pretrained("ZachBeesley/Spam-Detector")
-model = AutoModelForSequenceClassification.from_pretrained("ZachBeesley/Spam-Detector")
-
 # Function to process the input text and return the predicted label
 def predict(text):
-    # Use the pipeline to classify the text
-    result = pipe(text)
-
-    # Extract the predicted label and confidence score
-    label = result[0]["label"]
-    confidence = result[0]["score"]
-
-    # Return the result
-    return f"Predicted label: {label}\nConfidence: {confidence:.2f}"
+    try:
+        # Use the pipeline to classify the text
+        result = pipe(text)
+        
+        # Extract the predicted label and confidence score
+        label = result[0]["label"]
+        confidence = result[0]["score"]
+
+        # Return the result
+        return f"Predicted label: {label}\nConfidence: {confidence:.2f}"
+    except Exception as e:
+        # Handle errors
+        return f"Error: {str(e)}"
 
 # Create the Gradio interface
 iface = gr.Interface(