Update app.py

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
 from transformers import pipeline, VisionEncoderDecoderModel, ViTImageProcessor
 from PIL import Image
-import fitz 
+import fitz  # PyMuPDF for PDF processing
 import logging
 from concurrent.futures import ThreadPoolExecutor
 import torch
@@ -17,9 +17,9 @@ def setup_logging():
 @st.cache_resource
 def load_models():
     logging.info("Loading Hugging Face models...")
-    # Load image-to-text model from Hugging Face
-    processor = ViTImageProcessor.from_pretrained("microsoft/vision-transformation-transformer")
-    model = VisionEncoderDecoderModel.from_pretrained("microsoft/vision-transformation-transformer")
+    # Use an alternative model from Hugging Face for image captioning
+    processor = ViTImageProcessor.from_pretrained("google/vit-base-patch16-224")
+    model = VisionEncoderDecoderModel.from_pretrained("google/vit-base-patch16-224")
     
     # Load translation models
     translator_hi = pipeline("translation", model="Helsinki-NLP/opus-mt-en-hi")