Update README.md

README.md

@@ -28,4 +28,11 @@ In training of the model, we used the following data sources:
 
 ## Usage
 
-When using this model, make sure that your speech input is sampled at 16kHz.
+```python
+from speechbrain.inference.interfaces import foreign_class
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+asr_classifier = foreign_class(source="Macedonian-ASR/wav2vec2-aed-macedonian-asr", pymodule_file="custom_interface.py", classname="ASR")
+asr_classifier = asr_classifier.to(device)
+predictions = asr_classifier.classify_file("audio_file.wav", device)
+print(predictions)
+```