huangyuxin
|
e1a2cfef7f
|
fix the resume bug: the lr is not related to iteration, but epoch
|
3 years ago |
|
huangyuxin
|
61fe292c47
|
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into ds2_online
|
3 years ago |
|
huangyuxin
|
718ae52e3f
|
add from_config function to ds2_oneline and ds2
|
3 years ago |
|
huangyuxin
|
7a3d164122
|
fix the bidirect rnn, add deepspeech2.yaml for aishell, tiny, librispeech
|
3 years ago |
|
huangyuxin
|
85d5021475
|
reconstruct the exp/model.py and the model.export()
|
3 years ago |
Hui Zhang
|
e76123d418
|
rm useless
|
3 years ago |
|
Hui Zhang
|
820b4db287
|
with all args for scheduler
|
3 years ago |
|
Hui Zhang
|
c4da9a7f3a
|
filter key by class signature, no print tensor
|
3 years ago |
|
Hui Zhang
|
3912c255ef
|
support noam lr and opt
|
3 years ago |
|
Hui Zhang
|
1cd4d4bf83
|
fix tiny conf and refactor optimizer and scheduler
|
3 years ago |
|
Hui Zhang
|
cc813b18d3
|
fix install and format code
|
3 years ago |
|
huangyuxin
|
319228653e
|
fix some small mistakes
|
3 years ago |
|
huangyuxin
|
61d8540451
|
reconstruct the export function and the run.sh in aishell and librispeech
|
3 years ago |
Junkun
|
515497ae1f
|
refine the code
|
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 |
|
Junkun
|
0323151912
|
add u2 st
|
3 years ago |
|
huangyuxin
|
3fb9f6885a
|
complete model export for ds2_online
|
3 years ago |
|
Hui Zhang
|
ccdfd5b342
|
format
|
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 |
|
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
|
d398270f95
|
æå增加了chunk_by_chunk,初步测试å通过ã
|
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 |
|
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
|
2cacbaf48e
|
修改了deepspeech2.py部分LSTM和GRU的代码，增加了LayerNorm
|
3 years ago |
|
huangyuxin
|
ce1e8ab5b6
|
change the dir
|
3 years ago |
|
Hui Zhang
|
fd8a4ec179
|
Merge pull request #729 from PaddlePaddle/fst
TLG graph
|
3 years ago |
|
Hui Zhang
|
ab5411ec16
|
Merge pull request #698 from yt605155624/thchs30_MFA
Thchs30 mfa
|
3 years ago |
|
Hui Zhang
|
104743cccc
|
TLG build pass
|
3 years ago |
|
Hui Zhang
|
b076d3e9bb
|
fix autolog install; only autolog in test, or will hangup
|
3 years ago |
|
Jackwaterveg
|
ec19248f38
|
autoLog
|
3 years ago |
|
Jackwaterveg
|
48e877375d
|
change autoLog
|
3 years ago |
huangyuxin
|
d2db706384
|
added autolog
|
3 years ago |
|
huangyuxin
|
3fffd57e8b
|
added autoLog, but gpu_util is always 0.0%
|
3 years ago |
|
huangyuxin
|
fc88745782
|
revise load parameters
|
3 years ago |
