Update README

README.md

@@ -13,4 +13,15 @@ The base model is pre-trained on 16kHz sampled speech audio from Vietnamese spee
 [Paper](https://arxiv.org/abs/2006.11477)
 
 # Usage
-See [this notebook](https://colab.research.google.com/drive/1FjTsqbYKphl9kL-eILgUc-bl4zVThL8F?usp=sharing) for more information on how to fine-tune the English pre-trained model.
+See [this notebook](https://colab.research.google.com/drive/1FjTsqbYKphl9kL-eILgUc-bl4zVThL8F?usp=sharing) for more information on how to fine-tune the English pre-trained model.
+
+```python
+import torch
+from transformers import Wav2Vec2Model
+
+model = Wav2Vec2Model.from_pretrained("dragonSwing/viwav2vec2-base-3k")
+
+# Sanity check
+inputs = torch.rand([1, 16000])
+outputs = model(inputs)
+```