app

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+from transformers import TFDistilBertForSequenceClassification, DistilBertTokenizerFast
+
+# Load the model and tokenizer from Hugging Face Hub
+model_name = "HamOrSpam_Model"  # Replace with your actual model path
+tokenizer = DistilBertTokenizerFast.from_pretrained(model_name)
+model = TFDistilBertForSequenceClassification.from_pretrained(model_name)
+
+def classify_text(text):
+    # Tokenize the text input and prepare it for the model
+    inputs = tokenizer(text, return_tensors="tf", truncation=True, padding=True, max_length=512)
+
+    # Get model predictions
+    predictions = model(inputs.data)[0]
+
+    # Convert predictions to probabilities using softmax
+    probabilities = tf.nn.softmax(predictions, axis=-1)
+
+    # Get the higher probability index
+    prediction_index = tf.argmax(probabilities, axis=-1).numpy()[0]
+
+    # Convert the index to label
+    label = "ham" if prediction_index == 0 else "spam"
+
+    # Return the label and the probabilities of each class
+    return {"label": label, "probabilities": probabilities.numpy().tolist()}
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=classify_text,
+    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter Text Here..."),
+    outputs=[
+        gr.outputs.Label(label="Classification"),
+        gr.outputs.JSON(label="Probabilities")
+    ]
+)
+
+# Launch the app
+iface.launch()