Update README.md

README.md

@@ -75,7 +75,7 @@ There is no need for `ecapa2_model.eval()` or `torch.no_grad()`, this is done au
 For the extraction of other hierachical features, the `label` argument can be used, which accepts a string containing the feature ids separated with '|':
 
 ```python
-# only extracts embedding, same as previous example
+# default, only extract the embedding
 feature = ecapa2_model(audio, label='embedding')
 
 # concatenates the gfe_1, pool and embedding features