Upload app.py

app.py

@@ -4,7 +4,7 @@ import pytesseract
 import PyPDF2
 from pdf2image import convert_from_path
 from PIL import Image
-import doctr
+
 
 
 def extract_text(file_path):
@@ -18,11 +18,10 @@ def extract_text(file_path):
             text = page.extract_text()
             st.write(text)  # Display the extracted selectable text
 
-    model = doctr.models.OCR()
-    images = model(file_path)  # Convert PDF pages to images
-    for i, page in enumerate(images.pages):
+    images = convert_from_path(file_path)  # Convert PDF pages to images
+    for i, image in enumerate(images):
         st.write(f"Page {i + 1}")
-        text = page.content
+        text = pytesseract.image_to_string(image)
         st.write(text)  # Display the extracted text from the image
 
 def main():