dragonSwing commited on
Commit
4b45541
1 Parent(s): bb37e85

Update README

Browse files
Files changed (1) hide show
  1. README.md +12 -1
README.md CHANGED
@@ -13,4 +13,15 @@ The base model is pre-trained on 16kHz sampled speech audio from Vietnamese spee
13
  [Paper](https://arxiv.org/abs/2006.11477)
14
 
15
  # Usage
16
- 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.
 
 
 
 
 
 
 
 
 
 
 
 
13
  [Paper](https://arxiv.org/abs/2006.11477)
14
 
15
  # Usage
16
+ 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.
17
+
18
+ ```python
19
+ import torch
20
+ from transformers import Wav2Vec2Model
21
+
22
+ model = Wav2Vec2Model.from_pretrained("dragonSwing/viwav2vec2-base-3k")
23
+
24
+ # Sanity check
25
+ inputs = torch.rand([1, 16000])
26
+ outputs = model(inputs)
27
+ ```