Update app.py

app.py

@@ -13,24 +13,14 @@ explainer = AutoModelForSequenceClassification.from_pretrained("gpt2")
 def extract_text(image):
     return ocr_reader.readtext(image)
 
+# Define a function to process OCR results and extract actual text
+def process_ocr_results(ocr_results):
+    extracted_text = " ".join([res[1] for res in ocr_results])
+    return extracted_text
+
 # Define a function to explain the extracted text
 def explain_text(text):
-    tokenizer = AutoTokenizer.from_pretrained("gpt2")
-    
-    # Set pad_token to eos_token (end of sequence token)
-    tokenizer.pad_token = tokenizer.eos_token
-    
-    # Convert the text to a string if necessary
-    if not isinstance(text, str):
-        text = str(text)
-
-    # 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)
+    explanation = "The extracted text is: " + text
     return explanation
 
 # Create a Streamlit layout
@@ -44,11 +34,9 @@ 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)
+    ocr_results = extract_text(image)
+    extracted_text = process_ocr_results(ocr_results)
 
     # Explain the extracted text
     explanation = explain_text(extracted_text)