Update README.md

README.md

@@ -27,28 +27,27 @@ Or with Conda:
 conda install -c conda-forge huggingface_hub
 ```
 
-Now you can download the model by executing the following code:
-
-```
-from huggingface_hub import hf_hub_download
-
-model_file = hf_hub_download(repo_id='Jenthe/ECAPA2', filename='model.pt')
-```
-
-Subsequent calls will load the previously downloaded model automatically.
-
 ### Speaker Embedding Extraction
 
 Extracting speaker embeddings is easy and only requires a few lines of code:
+
 ```
 import torch
 import torchaudio
+from huggingface_hub import hf_hub_download
+
+model_file = hf_hub_download(repo_id='Jenthe/ECAPA2', filename='model.pt')
+model = torch.jit.load(model_file, map_location='cpu')
 
-audio = torchaudio.load('sample.wav')
+audio, sr = torchaudio.load('sample.wav')
 model = torch.jit.load(model_file, map_location='cpu')
 embedding = model.extract_embedding(audio)
 ```
 
+Subsequent calls will load the previously downloaded model automatically.
+
+Note: input audio should have a sample rate of 16 kHz.
+
 ### Hierarchical Feature Extraction
 
 For the extraction of other hierachical features, a separate model function is provided: