From eab833c7a744954080adc83e942dbbe8b6c2c7db Mon Sep 17 00:00:00 2001
From: dohe0342 <kimdohe1070@gmail.com>
Date: Tue, 11 Apr 2023 15:47:55 +0900
Subject: [PATCH] from local

---
 .../.data2vec_audio.py.swp                    | Bin 40960 -> 40960 bytes
 .../data2vec_audio.py                         |   2 +-
 2 files changed, 1 insertion(+), 1 deletion(-)

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 05986257145cf4035c8de7dcc38a54b872460d72..dec1fc554d99ff003a8ac2fe24670aad79d7476b 100644
GIT binary patch
delta 152
zcmZoTz|?SnNi4}A%+puFQqO<^2m}}yN|;PjPR-aT_RgL)nT3I2_GC_n?}khq3=H?#
z85k;nSPzKVftU@5Z?Z8k+yLS&KwJRCnn3)B6{u^op<@=y<kzmUn-99CGszd1BqnET
rL>Cn0=N6RcD5Rw(mXsEy7RTx+q-5sW8ct615SjeTU3PQ6$HZ^|;KwN|

delta 142
zcmZoTz|?SnNi4}A%+puFQqO<^2m}}y${9>kwoTh8_RgL)hlPP*$z)E4?}pqQ3=A*W
z85kOY*c^xjfS4bMAF(koJOtvsKwJsLMnL?U6{u^op<@=y<bb)HlMCErH}7ywXPW%q
hgH^DgC_lHLL`NYlHL;|$D783ta-xUG<{*!C;Q)3pCH4RS

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 34ce40466..b2fff73d8 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
@@ -494,7 +494,7 @@ class Data2VecAudioModel(BaseFairseqModel):
             prompt = prompt.expand((features.size()[0], prompt.size()[0], prompt.size()[1]))
             print(prompt.size())
             print(features.size())
-            features = torch.cat([prompt, features])
+            features = torch.stack([prompt, features], dim=1)
             print(features.size())
             prompt_padding_mask = torch.zeros(promt.size()).type(torch.BoolTensor).to(features.device)
             padding_mask = torch.cat([prompt_padding_mask, padding_mask])