diff --git a/examples/detect_from_microphone.py b/examples/detect_from_microphone.py
index f72b084..7c21e10 100644
--- a/examples/detect_from_microphone.py
+++ b/examples/detect_from_microphone.py
@@ -27,6 +27,20 @@ parser.add_argument(
     default=1280,
     required=True
 )
+parser.add_argument(
+    "--model_path",
+    help="The path of a specific model to load",
+    type=str,
+    default="",
+    required=False
+)
+parser.add_argument(
+    "--inference_framework",
+    help="The inference framework to use (either 'onnx' or 'tflite'",
+    type=str,
+    default='tflite',
+    required=False
+)
 
 args=parser.parse_args()
 
@@ -39,7 +53,12 @@ audio = pyaudio.PyAudio()
 mic_stream = audio.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK)
 
 # Load pre-trained openwakeword models
-owwModel = Model()
+if args.model_path != "":
+    owwModel = Model(wakeword_models=[args.model_path], inference_framework=args.inference_framework)
+else:
+    owwModel = Model(inference_framework=args.inference_framework)
+
+n_models = len(owwModel.models.keys())
 
 # Run capture loop continuosly, checking for wakewords
 if __name__ == "__main__":
@@ -48,7 +67,7 @@ if __name__ == "__main__":
     print("#"*100)
     print("Listening for wakewords...")
     print("#"*100)
-    print("\n"*13)
+    print("\n"*(n_models*3))
 
     while True:
         # Get audio
@@ -73,5 +92,5 @@ if __name__ == "__main__":
             """
 
         # Print results table
-        print("\033[F"*14)
+        print("\033[F"*(4*n_models+1))
         print(output_string_header, "                             ", end='\r')
diff --git a/openwakeword/utils.py b/openwakeword/utils.py
index 3a6411f..fbefd39 100644
--- a/openwakeword/utils.py
+++ b/openwakeword/utils.py
@@ -438,6 +438,7 @@ def bulk_predict(
                  wakeword_models: List[str],
                  prediction_function: str = 'predict_clip',
                  ncpu: int = 1,
+                 inference_framework = "tflite",
                  **kwargs
                  ):
     """
@@ -445,10 +446,14 @@ def bulk_predict(
 
     Args:
         input_paths (List[str]): The list of input file to predict
-        wakeword_model_path (List[str])): The paths to the wakeword ONNX model files
+        wakeword_models (List[str])): The paths to the wakeword model files
         prediction_function (str): The name of the method used to predict on the input audio files
                                    (default is the `predict_clip` method)
         ncpu (int): How many processes to create (up to max of available CPUs)
+        inference_framework (str): The inference framework to use when for model prediction. Options are
+                                    "tflite" or "onnx". The default is "tflite" as this results in better
+                                    efficiency on common platforms (x86, ARM64), but in some deployment
+                                    scenarios ONNX models may be preferable.
         kwargs (dict): Any other keyword arguments to pass to the model initialization or
                        specified prediction function
 
@@ -472,6 +477,7 @@ def bulk_predict(
                            if key in openwakeword.Model.__init__.__code__.co_varnames}
         oww = openwakeword.Model(
             wakeword_models=wakeword_models,
+            inference_framework=inference_framework,
             **filtered_kwargs
         )
         mdls.append(oww)