Update app.py

app.py

@@ -12,12 +12,13 @@ def load_model():
 
 # Extract text from image
 def extract_text(image, processor, model):
-    # Preprocess image
-    inputs = processor(images=image, return_tensors="pt")
+    # Preprocess image (extract pixel values only)
+    inputs = processor(images=image, return_tensors="pt").to("cpu")
+    pixel_values = inputs.get("pixel_values")  # Only pass necessary inputs
 
     # Perform generation
     with torch.no_grad():
-        outputs = model.generate(**inputs)
+        outputs = model.generate(pixel_values=pixel_values)  # Use pixel_values here
 
     # Decode outputs
     result = processor.batch_decode(outputs, skip_special_tokens=True)[0]