Update app.py

app.py

@@ -4,7 +4,7 @@ from PIL import Image
 import gradio as gr
 import os
 
-# Load the OCR model and tokenizer with low memory usage in mind
+# Load the OCR model and tokenizer
 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, 
@@ -14,9 +14,12 @@ model = AutoModel.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True,
 device = torch.device('cpu')
 model = model.to(device)
 
-# Function to perform OCR on the image
-def perform_ocr(image):
-    # Save the uploaded image temporarily
+# Function to perform OCR on the image file
+def perform_ocr(image_file_path):
+    # Open the image using PIL
+    image = Image.open(image_file_path)
+
+    # Save the image temporarily
     temp_image_path = "temp_image.png"
     image.save(temp_image_path)
 
@@ -24,10 +27,10 @@ def perform_ocr(image):
     with torch.no_grad():
         # Perform OCR using the model (pass the file path of the saved image)
         result = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
-    
+
     # Clean up the temporary image file
     os.remove(temp_image_path)
-    
+
     # Return the extracted text
     return result