Update app.py

app.py

@@ -5,34 +5,34 @@ import gradio as gr
 import tempfile
 
 # 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, 
-                                  pad_token_id=tokenizer.eos_token_id).eval()
+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')
-model = model.to(device)
+# device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+# model = model.to(device)  # Uncomment if you want to use GPU
 
 # Function to perform OCR on the image
 def perform_ocr(image):
-    # Save the image to a temporary file
     with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as temp_file:
-        image.save(temp_file.name)  # Save the image
-        temp_image_path = temp_file.name  # Get the file path for the saved image
+        image.save(temp_file.name)
+        temp_image_path = temp_file.name
 
-    # Perform OCR using the model
-    result = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
-    return result
+        # Perform OCR using the model
+        result = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
+        return result
 
-# Create the Gradio interface using the new syntax
+# Create the Gradio interface
 interface = gr.Interface(
-    fn=perform_ocr, 
-    inputs=gr.Image(type="pil"),  # Updated to gr.Image
-    outputs=gr.Textbox(),         # Updated to gr.Textbox
+    fn=perform_ocr,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Textbox(),
     title="OCR Web App",
     description="Upload an image to extract text using the GOT-OCR2.0 model."
 )
 
 # Launch the app
-interface.launch()
+interface.launch()