From 1e32177f0cb1adc0a28c01a4d355113830ac3b58 Mon Sep 17 00:00:00 2001
From: dohe0342 <kimdohe1070@gmail.com>
Date: Tue, 11 Apr 2023 15:49:15 +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 dec1fc554d99ff003a8ac2fe24670aad79d7476b..da5c74255266bc0cc56a13b44988d42320d2bd0a 100644
GIT binary patch
delta 115
zcmZoTz|?SnNi@kI%+puFQqO<^2m}}yW;2<l{M#t{-kvp;g@Ix2WKM_ghAbQm3=i2E
z7^;BS0Ejt(m;;D!voSE-0^)5zTm;10K>UOisB5#KV-d^bGB@$fJ6zM5Cja+f-K^$u
GD;xm!I2+gi

delta 113
zcmZoTz|?SnNi@kI%+puFQqO<^2m}}yN|;PjPHhx@Z_k>{!oV<lGN;3LLnaOehWqRc
z3>84E2gK|^%m&0a*%%mZ0Pz+eE&yUpAb!LO)V0~rv4~~!Qr8+L*5Z=H<m}BV9(Te4
Dmf{*W

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 b2fff73d8..a82f51429 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.stack([prompt, features], dim=1)
+            features = torch.cat([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])