Update README.md

README.md

@@ -59,6 +59,9 @@ enhanced = enhance_model.enhance_batch(noisy, lengths=torch.tensor([1.]))
 torchaudio.save('enhanced.wav', enhanced.cpu(), 16000)
 ```
 
+### Inference on GPU
+To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
+
 ## Referencing MetricGAN+
 
 If you find MetricGAN+ useful, please cite:
@@ -83,6 +86,6 @@ title = {SpeechBrain},
 year = {2021},
 publisher = {GitHub},
 journal = {GitHub repository},
-howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
+howpublished = {\\\\\\\\url{https://github.com/speechbrain/speechbrain}},
 }
 ```