diff --git a/egs/librispeech/ASR/.decode.sh.swp b/egs/librispeech/ASR/.decode.sh.swp
index f5b7e9c49..797abcbb2 100644
Binary files a/egs/librispeech/ASR/.decode.sh.swp and b/egs/librispeech/ASR/.decode.sh.swp differ
diff --git a/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/.data2vec_audio.py.swp b/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/.data2vec_audio.py.swp
index 3ad50f7aa..090733575 100644
Binary files a/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/.data2vec_audio.py.swp and b/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/.data2vec_audio.py.swp differ
diff --git a/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/data2vec_audio.py b/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/data2vec_audio.py
index 383a98a00..7f0c5cf79 100644
--- a/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/data2vec_audio.py
+++ b/egs/librispeech/ASR/pruned_transducer_stateless_d2v_v2/data2vec_audio.py
@@ -495,6 +495,7 @@ class Data2VecAudioModel(BaseFairseqModel):
             features = torch.cat([prompt, features], dim=1)
             prompt_padding_mask = torch.zeros(prompt.size()[0], prompt.size()[1]).type(torch.BoolTensor).to(features.device)
             padding_mask = torch.cat([prompt_padding_mask, padding_mask], dim=1)
+            print(padding_mask.size())
 
         features = self.layer_norm(features)