From 6476c0715b8608a01b553002ca703350b33cd60e Mon Sep 17 00:00:00 2001 From: dohe0342 Date: Tue, 11 Apr 2023 15:53:21 +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 591c7ff5cc3f5fefd2ab594910f1a1eef2374771..d856a433dc41781ae181d7f34f0450c6ee59905b 100644 GIT binary patch delta 108 zcmZoTz|?SnNi4}A%+puFQqO<^2m}}ye3(sB!e(t0duPuo%fi4AIhoVpzitXU1A`e5 zzhPrwI10o^fOt9(PXpp2Al3uo=d2723xGIsv#FyB%jP^+H>SxaJ;XL|b@z?{05zK# AJOBUy delta 112 zcmZoTz|?SnNi4}A%+puFQqO<^2m}}y6q!v^QfF=yduPvT#KORkH<{DnziuTv1A{jZ zGXn7~HU@^9K)eQsR|9c75IY0$A65p2tw5Z&+0;>mWisDf@yUx^r8k$kYBFu!;_edx E0F68vVE_OC 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 32b06f290..3f95fec84 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 @@ -496,7 +496,7 @@ class Data2VecAudioModel(BaseFairseqModel): print(features.size()) features = torch.cat([prompt, features], dim=1) print(features.size()) - prompt_padding_mask = torch.zeros(prompt.size()).type(torch.BoolTensor).to(features.device) + prompt_padding_mask = torch.zeros(prompt.size()[0], prompt.size()[1]).type(torch.BoolTensor).to(features.device) print(prompt_padding_mask.size()) padding_mask = torch.cat([prompt_padding_mask, padding_mask]) print(padding_mask.size())