Update README.md

README.md

@@ -64,6 +64,9 @@ signal, fs =torchaudio.load('samples/audio_samples/example1.wav')
 embeddings = classifier.encode_batch(signal)
 ```
 
+The system is trained with recordings sampled at 16kHz (single channel).
+The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *classify_file* if needed. Make sure your input tensor is compliant with the expected sampling rate if you use *encode_batch* and *classify_batch*.
+
 ### Inference on GPU
 To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.