Update app.py

app.py

@@ -2,25 +2,24 @@ import streamlit as st
 import io
 from PIL import Image
 import torch
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import AutoTokenizer, AutoModelForCausalLM
 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")
+text_generator = AutoModelForCausalLM.from_pretrained("gpt2")
+text_tokenizer = AutoTokenizer.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 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):
-    explanation = "The extracted text is: " + text
+    # Generate an explanation using the text generation model (GPT-2)
+    input_ids = text_tokenizer.encode(text, return_tensors="pt")
+    explanation_ids = text_generator.generate(input_ids, max_length=50, num_return_sequences=1)
+    explanation = text_tokenizer.decode(explanation_ids[0], skip_special_tokens=True)
     return explanation
 
 # Create a Streamlit layout
@@ -36,7 +35,7 @@ if uploaded_file is not None:
 
     # Extract text from the image
     ocr_results = extract_text(image)
-    extracted_text = process_ocr_results(ocr_results)
+    extracted_text = " ".join([res[1] for res in ocr_results])
 
     # Explain the extracted text
     explanation = explain_text(extracted_text)