a43992899 commited on
Commit
d049b5e
1 Parent(s): 53f05da

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -46,6 +46,7 @@ print(time_reduced_hidden_states.shape) # [13, 768]
46
  # you can even use a learnable weighted average representation
47
  aggregator = nn.Conv1d(in_channels=13, out_channels=1, kernel_size=1)
48
  weighted_avg_hidden_states = aggregator(time_reduced_hidden_states).squeeze()
 
49
  ```
50
 
51
  Our model is based on the [data2vec audio model](https://huggingface.co/docs/transformers/model_doc/data2vec#transformers.Data2VecAudioModel).
 
46
  # you can even use a learnable weighted average representation
47
  aggregator = nn.Conv1d(in_channels=13, out_channels=1, kernel_size=1)
48
  weighted_avg_hidden_states = aggregator(time_reduced_hidden_states).squeeze()
49
+ print(weighted_avg_hidden_states.shape)
50
  ```
51
 
52
  Our model is based on the [data2vec audio model](https://huggingface.co/docs/transformers/model_doc/data2vec#transformers.Data2VecAudioModel).