Update app.py

app.py

@@ -1,32 +1,33 @@
 import torch
 from transformers import AutoModel, AutoTokenizer
 from PIL import Image
-import gradio as gr
 
-# Load the OCR model and tokenizer
+# Load the OCR model and tokenizer with low memory usage in mind
 tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
 model = AutoModel.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True, 
                                   low_cpu_mem_usage=True, 
                                   pad_token_id=tokenizer.eos_token_id).eval()
 
-# Check if GPU is available and use it, else use CPU
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+# Ensure we are using CPU
+device = torch.device('cpu')
 model = model.to(device)
 
 # Function to perform OCR on the image
-def perform_ocr(image):
-    # Perform OCR using the model
-    result = model.chat(tokenizer, image, ocr_type='ocr')
+def perform_ocr(image_path):
+    # Open the image file
+    image = Image.open(image_path)
+
+    # Use torch.no_grad() to avoid unnecessary memory usage
+    with torch.no_grad():
+        # Perform OCR using the model
+        result = model.chat(tokenizer, image_path, ocr_type='ocr')
+    
+    # Return the extracted text
     return result
 
-# Create the Gradio interface using the new syntax
-interface = gr.Interface(
-    fn=perform_ocr, 
-    inputs=gr.Image(type="pil"),  # Updated to gr.Image
-    outputs=gr.Textbox(),         # Updated to gr.Textbox
-    title="OCR Web App",
-    description="Upload an image to extract text using the GOT-OCR2.0 model."
-)
+# Example usage with an image file path
+image_path = "/content/id.jpg"
+extracted_text = perform_ocr(image_path)
 
-# Launch the app
-interface.launch(share=True)
+# Output the extracted text
+print("Extracted Text:", extracted_text)