Update app.py

app.py

@@ -1,9 +1,11 @@
 import streamlit as st
 from PIL import Image
-import io
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 from easyocr import Reader
 
+# Initialize the image-to-text model
+image_to_text = pipeline("image-to-text", model="Salesforce/blip-image-captioning-large")
+
 # Load the OCR model and text explanation model
 ocr_reader = Reader(['en'])
 
@@ -37,11 +39,15 @@ uploaded_file = st.file_uploader("Upload an image:")
 if uploaded_file is not None:
     image = Image.open(uploaded_file)
     ocr_results = extract_text(image)
+    image_caption = image_to_text(image)  # Use the image-to-text model
     explanation = explain_text(ocr_results, text_generator, text_tokenizer)
 
     st.markdown("**Extracted text:**")
     st.markdown(" ".join([res[1] for res in ocr_results]))
 
+    st.markdown("**Image Caption:**")
+    st.markdown(image_caption[0]['caption'])  # Display the image caption
+
     st.markdown("**Explanation:**")
     st.markdown(explanation)