huangyuxin
|
b53171694e
|
releace the <space> with ' ' in ctcdecoder
|
3 years ago |
Hui Zhang
|
dd06472432
|
extract ctc_align into ctc_utils
|
3 years ago |
|
Hui Zhang
|
8b45c3e65e
|
refactor trainer.py and rm ueseless dir setup code
|
3 years ago |
|
Hui Zhang
|
466672e1de
|
no_sync if paddle support else nullcontext
|
3 years ago |
|
Hui Zhang
|
856d641c9c
|
multi worker for dataloader
|
3 years ago |
|
Hui Zhang
|
0c08915207
|
ctc using nn.Dropout; ds2 libri vald batch_size / 4
|
3 years ago |
|
huangyuxin
|
08281eca72
|
fix bug: bug of space id in score.cpp, add detokenize
|
3 years ago |
|
Hui Zhang
|
9d5eb74066
|
fix decode json file
|
3 years ago |
|
Hui Zhang
|
ae87bc8c7a
|
dump decode result as jsonlines
|
3 years ago |
|
Hui Zhang
|
c6e8a33b73
|
fix set_device; more utils; args.opts support multi same name
|
3 years ago |
|
Hui Zhang
|
913b2300c3
|
nprocs 0 for cpu, other for gpu
|
3 years ago |
|
Hui Zhang
|
054e099b28
|
format
|
3 years ago |
|
Hui Zhang
|
0e91d26ae3
|
fix log; add report to trainer
|
3 years ago |
|
Hui Zhang
|
576e94da04
|
log interval 1 when benchmark
|
3 years ago |
|
Hui Zhang
|
d7a33b9d5e
|
update config with contextlib
|
3 years ago |
|
Hui Zhang
|
7e136d0893
|
support no_sync for backward; ds support accum grad
|
3 years ago |
|
huangyuxin
|
2451a177b0
|
fix paddling len bug
|
3 years ago |
|
huangyuxin
|
317ffea5e5
|
simplify the code
|
3 years ago |
|
huangyuxin
|
1f050a4d01
|
make the code simple
|
3 years ago |
|
huangyuxin
|
0d0b581181
|
add static_forward_online and static_forward_offline
|
3 years ago |
|
huangyuxin
|
db042a2974
|
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into ds2_online_export
|
3 years ago |
|
huangyuxin
|
b585684bf4
|
add function: test export
|
3 years ago |
|
huangyuxin
|
2d3b2aed05
|
add seed in argparse
|
3 years ago |
|
huangyuxin
|
9068c0d4f9
|
Merge branch 'HEAD_1' into ds2_online
|
3 years ago |
|
huangyuxin
|
718407b77d
|
add seed
|
3 years ago |
|
huangyuxin
|
e1a2cfef7f
|
fix the resume bug: the lr is not related to iteration, but epoch
|
3 years ago |
|
huangyuxin
|
718ae52e3f
|
add from_config function to ds2_oneline and ds2
|
3 years ago |
|
huangyuxin
|
85d5021475
|
reconstruct the exp/model.py and the model.export()
|
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 |
|
huangyuxin
|
722c55e4c5
|
reconstruct the rnn state, from list to tensor
|
3 years ago |
|
huangyuxin
|
8f062cad6b
|
fixed the small problems
|
3 years ago |
|
huangyuxin
|
3fb9f6885a
|
complete model export for ds2_online
|
3 years ago |
|
huangyuxin
|
e8a3913422
|
merge develop_ds2_online
|
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
|
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
|
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
|
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 |
Haoxin Ma
|
d55e6b5a0a
|
revise from_pretrained function
|
4 years ago |
