Update README.md

README.md

@@ -12,6 +12,31 @@ ECAPA2 is a hybrid neural network architecture and training strategy for speaker
 
 ## Usage Guide
 
+### Download model
+
+You need to install the huggingface_hub package to download the ECAPA2 model:
+
+```
+pip install --upgrade huggingface_hub
+```
+
+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')
+model = torch.jit.load(model_file, map_location='cpu')
+```
+
+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:
@@ -20,8 +45,7 @@ import torch
 import torchaudio
 
 audio = torchaudio.load('sample.wav')
-ecapa2_model = torch.load('model.pt')
-embedding = ecapa2_model.extract_embedding(audio)
+embedding = model.extract_embedding(audio)
 ```
 
 ### Hierarchical Feature Extraction