Update README.md

README.md

@@ -38,18 +38,26 @@ from huggingface_hub import hf_hub_download
 
 # automatically checks for cached file
 model_file = hf_hub_download(repo_id='Jenthe/ECAPA2', filename='model.pt')
-model = torch.jit.load(model_file, map_location='cpu')
+ecapa2_model = torch.jit.load(model_file, map_location='cpu')
 
 # input audio should have a sample rate of 16 kHz
 audio, sr = torchaudio.load('sample.wav')
-embedding = model(audio)
+embedding = ecapa2_model(audio)
 ```
 
 ### Hierarchical Feature Extraction
 
-For the extraction of other hierachical features, a separate model function is provided:
+For the extraction of other hierachical features, the 'label' argument can be used, which accepts a string containing the feature ids separated with '|':
+
 ```
-feature = ecapa2_model.extract_feature(label='gfe1', type='mean')
+# only extracts embedding, same as previous example
+feature = ecapa2_model(audio, label='embedding')
+
+# concatenates the gfe_1, pool and embedding features
+feature = ecapa2_model(audio, label='gfe_1|pool|embedding')
+
+# returns the same output as previous example, concatenation always follows the order of the network
+feature = ecapa2_model(audio, label='embedding|gfe_1|pool')
 ```
 
 The following table describes the available features: