Update app.py

app.py

@@ -5,22 +5,48 @@ import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 from easyocr import Reader
 
+# Load the OCR model and text explanation model (gpt-2 as an example)
 ocr_reader = Reader(['en'])
 explainer = AutoModelForSequenceClassification.from_pretrained("gpt2")
+
+# Define a function to extract text from an image
 def extract_text(image):
     return ocr_reader.readtext(image)
+
+# Define a function to explain the extracted text
 def explain_text(text):
     tokenizer = AutoTokenizer.from_pretrained("gpt2")
-    input_ids = tokenizer.encode(text, return_tensors="pt")
-    explanation = explainer(input_ids)
+    
+    # Encode the text and convert to PyTorch tensors
+    inputs = tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512)
+    
+    input_ids = inputs["input_ids"]
+    attention_mask = inputs["attention_mask"]
+
+    explanation = explainer(input_ids, attention_mask=attention_mask)
     return explanation
+
+# Create a Streamlit layout
 st.title("Text Classification Model")
+
+# Allow users to upload an image
 uploaded_file = st.file_uploader("Upload an image:")
+
+# Extract text from the uploaded image
 if uploaded_file is not None:
+    # Read the uploaded image
     image = Image.open(uploaded_file)
     
+    # Process the image and convert to NumPy array if necessary
+    # image = process_image(image)
+
+    # Extract text from the image
     extracted_text = extract_text(image)
+
+    # Explain the extracted text
     explanation = explain_text(extracted_text)
+
+    # Display the extracted text and explanation
     st.markdown("**Extracted text:**")
     st.markdown(extracted_text)