Skip to content

GitLab

You need to sign in or sign up before continuing.
Commit 6e334a46 authored by Zhaoheng Ni's avatar Zhaoheng Ni Committed by Facebook GitHub Bot
Browse files

Fix initialization in hubert_pretrain_model (#2846) 

Summary:
address https://github.com/pytorch/audio/issues/2845

Pull Request resolved: https://github.com/pytorch/audio/pull/2846

Reviewed By: carolineechen

Differential Revision: D41251624

Pulled By: nateanl

fbshipit-source-id: 1a363d2314d6a452f35c109b9730da64ada5a2fd
parent eabf1a13
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 0 deletions
torchaudio/models/wav2vec2/components.py
View file @ 6e334a46
...@@ -199,6 +199,7 @@ class ConvolutionalPositionalEmbedding(Module): ...@@ -199,6 +199,7 @@ class ConvolutionalPositionalEmbedding(Module):
): ):
super().__init__() super().__init__()
self.embed_dim = embed_dim self.embed_dim = embed_dim
self.kernel_size = kernel_size
self.conv = nn.Conv1d( self.conv = nn.Conv1d(
in_channels=embed_dim, in_channels=embed_dim,
out_channels=embed_dim, out_channels=embed_dim,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment