diff --git a/frigate/data_processing/common/license_plate/mixin.py b/frigate/data_processing/common/license_plate/mixin.py
index 778c059214..2606661bef 100644
--- a/frigate/data_processing/common/license_plate/mixin.py
+++ b/frigate/data_processing/common/license_plate/mixin.py
@@ -789,9 +789,7 @@ class LicensePlateProcessingMixin:
         input_w = int(input_h * max_wh_ratio)
 
         # check for model-specific input width
-        model_input_w = self.model_runner.recognition_model.runner.ort.get_inputs()[
-            0
-        ].shape[3]
+        model_input_w = self.model_runner.recognition_model.runner.get_input_width()
         if isinstance(model_input_w, int) and model_input_w > 0:
             input_w = model_input_w
 
diff --git a/frigate/embeddings/maintainer.py b/frigate/embeddings/maintainer.py
index be7843c9c0..1b5317ba86 100644
--- a/frigate/embeddings/maintainer.py
+++ b/frigate/embeddings/maintainer.py
@@ -108,7 +108,7 @@ class EmbeddingMaintainer(threading.Thread):
 
         # model runners to share between realtime and post processors
         if self.config.lpr.enabled:
-            lpr_model_runner = LicensePlateModelRunner(self.requestor)
+            lpr_model_runner = LicensePlateModelRunner(self.requestor, device="AUTO")
 
         # realtime processors
         self.realtime_processors: list[RealTimeProcessorApi] = []
diff --git a/frigate/embeddings/onnx/runner.py b/frigate/embeddings/onnx/runner.py
index 7badae3258..645b99204c 100644
--- a/frigate/embeddings/onnx/runner.py
+++ b/frigate/embeddings/onnx/runner.py
@@ -65,6 +65,31 @@ class ONNXModelRunner:
         elif self.type == "ort":
             return [input.name for input in self.ort.get_inputs()]
 
+    def get_input_width(self):
+        """Get the input width of the model regardless of backend."""
+        if self.type == "ort":
+            return self.ort.get_inputs()[0].shape[3]
+        elif self.type == "ov":
+            input_info = self.interpreter.inputs
+            first_input = input_info[0]
+
+            try:
+                partial_shape = first_input.get_partial_shape()
+                # width dimension
+                if len(partial_shape) >= 4 and partial_shape[3].is_static:
+                    return partial_shape[3].get_length()
+
+                # If width is dynamic or we can't determine it
+                return -1
+            except Exception:
+                try:
+                    # gemini says some ov versions might still allow this
+                    input_shape = first_input.shape
+                    return input_shape[3] if len(input_shape) >= 4 else -1
+                except Exception:
+                    return -1
+        return -1
+
     def run(self, input: dict[str, Any]) -> Any:
         if self.type == "ov":
             infer_request = self.interpreter.create_infer_request()