Junkun
|
45e71a0a64
|
correct yaml
|
3 years ago |
Junkun
|
515497ae1f
|
refine the code
|
3 years ago |
Hui Zhang
|
566f636cc6
|
Merge pull request #743 from LittleChenCc/develop
ST-related code and script for TED-En-Zh translation
|
3 years ago |
Hui Zhang
|
20d6f9ae4b
|
Merge pull request #745 from PaddlePaddle/s2
kaldi style data for u2 model
|
3 years ago |
Hui Zhang
|
9c00c5f804
|
Merge pull request #744 from PaddlePaddle/s1
update librispeech chunk conformer result
|
3 years ago |
Hui Zhang
|
3864e11302
|
update librispeech chunk conformer result
|
3 years ago |
Hui Zhang
|
dc44f552a1
|
update readme
|
3 years ago |
Junkun
|
9d05a749e2
|
script for TED-En-Zh translation
|
3 years ago |
Junkun
|
ac0ae57ef2
|
add collactor and evaluation code for ST
|
3 years ago |
huangyuxin
|
722c55e4c5
|
reconstruct the rnn state, from list to tensor
|
3 years ago |
huangyuxin
|
8f062cad6b
|
fixed the small problems
|
3 years ago |
Hui Zhang
|
2fd43efb3b
|
librispeech s2 for kaldi feat
|
3 years ago |
Junkun
|
0323151912
|
add u2 st
|
3 years ago |
Hui Zhang
|
c44caa36f6
|
Merge pull request #742 from PaddlePaddle/install
setup.sh with tools/ make
|
3 years ago |
Hui Zhang
|
74f987aa8f
|
setup.sh with tools/ make
|
3 years ago |
huangyuxin
|
3fb9f6885a
|
complete model export for ds2_online
|
3 years ago |
Hui Zhang
|
254d753b1c
|
Merge pull request #741 from PaddlePaddle/utils
duration utils
|
3 years ago |
Hui Zhang
|
ccdfd5b342
|
format
|
3 years ago |
Hui Zhang
|
571b13c53f
|
add dur utils
|
3 years ago |
huangyuxin
|
e8a3913422
|
merge develop_ds2_online
|
3 years ago |
huangyuxin
|
2f64ae6495
|
not change decoder
|
3 years ago |
huangyuxin
|
6c484923a4
|
solve the conflicts
|
3 years ago |
huangyuxin
|
4b5cbe9a12
|
ds2_online alignment, include prob_chunk_forward, prob_chunk_by_chunk_forward
|
3 years ago |
Hui Zhang
|
64c75771ea
|
Merge pull request #740 from Jackwaterveg/fix_auto_log
fix the bug: can not use the CPU to test the model
|
3 years ago |
Hui Zhang
|
de520cee96
|
Merge pull request #739 from PaddlePaddle/k8
zh 8k egs
|
3 years ago |
huangyuxin
|
fccecf9976
|
add strip for CUDA_VISIBLE_DEVICES
|
3 years ago |
huangyuxin
|
eacad8cf60
|
fix the bug: can not use the CPU to test the model
|
3 years ago |
huangyuxin
|
18eb2cb5ed
|
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into ds2_online
|
3 years ago |
huangyuxin
|
d398270f95
|
æå增加了chunk_by_chunk,初步测试å通过ã
|
3 years ago |
Hui Zhang
|
7278cf9bbb
|
default chun with all
|
3 years ago |
Hui Zhang
|
1f2b4ab293
|
zh 8k egs
|
3 years ago |
huangyuxin
|
2537221b61
|
Complete the modification according to the comments
, but still need to be unit tested
|
3 years ago |
huangyuxin
|
745df04f28
|
complete the pipline of tiny
|
3 years ago |
huangyuxin
|
e4ef8ed31e
|
add the subsampling as conv
|
3 years ago |
Hui Zhang
|
8432b9b256
|
Merge pull request #737 from Jackwaterveg/fixing_bug
Fixing bug
|
3 years ago |
huangyuxin
|
b13630b1c5
|
修复了librispeech和mini_libirspeech
|
3 years ago |
huangyuxin
|
156e324bbb
|
注释了sever.sh的17-21行
|
3 years ago |
huangyuxin
|
6baf9f0620
|
跑通了deeppseech_online的流程
|
3 years ago |
Jackwaterveg
|
8716386464
|
Update model.py
|
3 years ago |
huangyuxin
|
2c8d28111a
|
fix some small mistakes
|
3 years ago |
huangyuxin
|
5dd9e2f8ec
|
先不暴露出online
|
3 years ago |
huangyuxin
|
6079a2495d
|
把ds2中的deepspeech2.py恢复了
|
3 years ago |
huangyuxin
|
66c59cdeae
|
adding pre-commit
|
3 years ago |
huangyuxin
|
7b201ba457
|
增加了online的模型,通过了测试,还需要搭建配套的实验流程代码
|
3 years ago |
huangyuxin
|
4f392e28b1
|
complete the encoder of ds_online
|
3 years ago |
huangyuxin
|
269eecb3be
|
新建ds2_online文件夹
|
3 years ago |
huangyuxin
|
c7071dd2b4
|
Merge branch 'develop' into dp2
|
3 years ago |
huangyuxin
|
2cacbaf48e
|
修改了deepspeech2.py部分LSTM和GRU的代码,增加了LayerNorm
|
3 years ago |
Hui Zhang
|
6076197b20
|
Merge pull request #733 from PaddlePaddle/fixtest
fix chunk mode test script
|
3 years ago |
Hui Zhang
|
a8fa07db73
|
Merge pull request #734 from Jackwaterveg/dp2
change the dir
|
3 years ago |