Updated with OCR model and Gradio integration

app.py

@@ -1,20 +1,20 @@
 import gradio as gr
 from transformers import pipeline
 
-# Load Hugging Face TroCR model for OCR
+# Load a Hugging Face OCR model for printed text
 ocr_model = pipeline('image-to-text', model='microsoft/trocr-base-printed')
 
 def analyze_image(image):
-    # Use TroCR to extract text from the image
-    result = ocr_model(image, max_new_tokens=500)
+    result = ocr_model(image)
+    return result[0]['generated_text'] if result else "No text could be extracted."
 
 # Gradio interface for image input
 demo = gr.Interface(
     fn=analyze_image,
     inputs=gr.Image(type="pil"),  # Upload an image
     outputs="text",  # Output the extracted text
-    title="Document OCR Analysis",
-    description="Upload an image of a document to extract text."
+    title="Invoice Text Extraction",
+    description="Upload an image of an invoice to extract text."
 )
 
 if __name__ == "__main__":

requirements.txt

@@ -3,4 +3,5 @@ transformers
 torch
 gradio
 datasets
-pytesseract
+pytesseract
+Pillow