Update README.md

README.md

@@ -64,7 +64,7 @@ audio, sr = torchaudio.load('sample.wav') # sample rate of 16 kHz expected
 embedding = ecapa2_model(audio)
 ```
 
-There is no need for `ecapa2_model.eval()` or to disable gradient calculations, this is done automatically.
+There is no need for `ecapa2_model.eval()` or `torch.no_grad()`, this is done automatically.
 
 ### Hierarchical Feature Extraction