Update README.md

README.md

@@ -65,6 +65,9 @@ score, prediction = verification.verify_files("speechbrain/spkrec-ecapa-voxceleb
 ```
  The prediction is 1 if the two signals in input are from the same speaker and 0 otherwise.
 
+### Inference on GPU
+To perform inference on the GPU, add  `run_opts={"device":"cuda"}`  when calling the `from_hparams` method.
+
 #### Referencing ECAPA-TDNN
 ```
 @inproceedings{DBLP:conf/interspeech/DesplanquesTD20,
@@ -93,6 +96,6 @@ score, prediction = verification.verify_files("speechbrain/spkrec-ecapa-voxceleb
     year = {2021},
     publisher = {GitHub},
     journal = {GitHub repository},
-    howpublished = {\\url{https://github.com/speechbrain/speechbrain}},
+    howpublished = {\\\\url{https://github.com/speechbrain/speechbrain}},
   }
 ```