Update app.py

app.py

@@ -1,15 +1,8 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
-import torch
-import torch.nn.functional as F
-from pptx import Presentation
-import re
+from transformers import pipeline
 
-# Load the pre-trained model and tokenizer using gr.load
-model = gr.load("models/Ahmed235/roberta_classification")
-
-# Tokenizer can be loaded using transformers directly
-tokenizer = AutoTokenizer.from_pretrained("Ahmed235/roberta_classification")
+# Create a text classification pipeline
+classifier = pipeline("text-classification", model="Ahmed235/roberta_classification", tokenizer="Ahmed235/roberta_classification")
 
 def extract_text_from_pptx(file_path):
     presentation = Presentation(file_path)
@@ -23,22 +16,12 @@ def extract_text_from_pptx(file_path):
 def predict_pptx_content(file_path):
     try:
         extracted_text = extract_text_from_pptx(file_path)
-        cleaned_text = re.sub(r'\s+', ' ', extracted_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)
+        # Perform inference using the pipeline
+        result = classifier(extracted_text)
 
-        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()
+        predicted_label = result[0]['label']
+        predicted_probability = result[0]['score']
 
         prediction = {
             "Predicted Label": predicted_label,