Update app.py

app.py

@@ -1,13 +1,12 @@
 import streamlit as st
 import pytesseract
-import cv2
+import pdfkit
 import numpy as np
 from PIL import Image
-import pdfkit
 from docx import Document
 from transformers import pipeline
 
-# Set up OCR pipeline (you can replace with Hugging Face model)
+# Set up OCR pipeline from Hugging Face (ensure the correct model is used)
 ocr_pipeline = pipeline("image-to-text", model="microsoft/trocr-base-handwritten")
 
 # Streamlit UI
@@ -17,14 +16,15 @@ st.title("Handwritten Text Extractor")
 uploaded_file = st.file_uploader("Upload an image", type=["jpg", "jpeg", "png"])
 
 if uploaded_file is not None:
+    # Open and display the uploaded image
     image = Image.open(uploaded_file)
     st.image(image, caption="Uploaded Image", use_column_width=True)
 
-    # Convert image to numpy array
-    image_np = np.array(image)
+    # Convert the image to RGB (if not already)
+    image = image.convert("RGB")
 
-    # Extract text using OCR model
-    extracted_text = ocr_pipeline(image_np)[0]['generated_text']
+    # Extract text using Hugging Face OCR model
+    extracted_text = ocr_pipeline(image)[0]['generated_text']
 
     # Display extracted text
     st.subheader("Extracted Text")
@@ -43,4 +43,3 @@ if uploaded_file is not None:
     # Download buttons
     st.download_button("Download as DOCX", data=open(docx_filename, "rb"), file_name=docx_filename)
     st.download_button("Download as PDF", data=open(pdf_filename, "rb"), file_name=pdf_filename)
-