Update app.py

app.py

@@ -2,44 +2,37 @@ import torch
 from transformers import AutoModel, AutoTokenizer
 from PIL import Image
 import gradio as gr
-import os
+import tempfile
 
-# Specify the revision ID you want to pin to
-revision_id = "your_revision_id_here"  # Replace with the actual revision ID
-
-# Load the OCR model and tokenizer with pinned revision
-tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', revision=revision_id, trust_remote_code=True)
-model = AutoModel.from_pretrained('ucaslcl/GOT-OCR2_0', revision=revision_id, trust_remote_code=True, 
+# 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()
 
-# Move model to CPU
-device = torch.device('cpu')
+# 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)
 
-# Function to perform OCR on an 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)
-
-    # Use torch.no_grad() to avoid unnecessary memory usage
-    with torch.no_grad():
-        # Perform OCR using the model on CPU (pass the file path of the saved image)
-        result = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
+# 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
 
-    # Clean up the temporary image file
-    os.remove(temp_image_path)
-
-    # Return the extracted text
+    # Perform OCR using the model
+    result = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
     return result
 
-# Gradio interface for file upload and OCR
-iface = gr.Interface(fn=perform_ocr, inputs="file", outputs="text", 
-                     title="OCR Application", description="Upload an image to extract text.")
-
-# Launch the Gradio app
-iface.launch()
+# 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."
+)
+
+# Launch the app
+interface.launch()