Update app.py

app.py

@@ -1,10 +1,15 @@
-import gradio as gr
 from pptx import Presentation
 import re
-from transformers import pipeline
+import gradio as gr
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+import torch.nn.functional as F
 
-# Create a summarization pipeline
-summarizer = pipeline("summarization", model="Falconsai/text_summarization")
+# Load the pre-trained model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("Ahmed235/roberta_classification")
+model = AutoModelForSequenceClassification.from_pretrained("Ahmed235/roberta_classification")
+device = torch.device("cpu")
+model = model.to(device)  # Move the model to the CPU
 
 def extract_text_from_pptx(file_path):
     presentation = Presentation(file_path)
@@ -20,11 +25,24 @@ def predict_pptx_content(file_path):
         extracted_text = extract_text_from_pptx(file_path)
         cleaned_text = re.sub(r'\s+', ' ', extracted_text)
 
-        # Summarize the cleaned text
-        summary = summarizer(cleaned_text, max_length=80, min_length=30, do_sample=False)[0]['summary_text']
+        # Tokenize and encode the cleaned text
+        input_encoding = tokenizer(cleaned_text, truncation=True, padding=True, return_tensors="pt")
+        input_encoding = {key: val.to(device) for key, val in input_encoding.items()}  # Move input tensor to CPU
+
+        # Perform inference
+        with torch.no_grad():
+            outputs = model(**input_encoding)
+            logits = outputs.logits
+
+        probabilities = F.softmax(logits, dim=1)
+
+        predicted_label_id = torch.argmax(logits, dim=1).item()
+        predicted_label = model.config.id2label[predicted_label_id]
+        predicted_probability = probabilities[0][predicted_label_id].item()
 
         prediction = {
-            "Summary": summary
+            "Predicted Label": predicted_label,
+            "Evaluation": f"Evaluate the topic according to {predicted_label} is: {predicted_probability}",
         }
 
         return prediction
@@ -38,10 +56,10 @@ def predict_pptx_content(file_path):
 iface = gr.Interface(
     fn=predict_pptx_content,
     inputs=gr.File(type="filepath", label="Upload PowerPoint (.pptx) file"),
-    outputs="text",  # Only output the summary
+    outputs=["text", "text"],  # Predicted Label, Evaluation
     live=False,  # Change to True for one-time analysis
     title="<h1 style='color: lightgreen; text-align: center;'>HackTalk Analyzer</h1>",
 )
 
 # Deploy the Gradio interface
-iface.launch(share=True)
+iface.launch(share=True)