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 77d91bd1c..3b4854b30 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 0ef1ef8d3..de4e0e96e 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
@@ -94,7 +94,7 @@ class TransformerEncoderAdapter(TransformerEncoder):
             dropout_probability = np.random.random() if self.layerdrop > 0 else 1
             if not self.training or (dropout_probability > self.layerdrop):
                 x, (z, lr) = layer(
-                    x, self_attn_padding_mask=padding_mask, need_weights=False, layer_num=i
+                    x, self_attn_padding_mask=padding_mask, need_weights=False,
                 )
                 x = self.adapters(x, layer_id=i)