Hui Zhang
|
259781768e
|
comment u2 model for easy understand
|
3 years ago |
Hui Zhang
|
2820537fcc
|
fix load param
|
3 years ago |
Hui Zhang
|
20117d99ee
|
fix ckpt load
|
3 years ago |
Hui Zhang
|
43b52082c3
|
Merge pull request #629 from PaddlePaddle/align
ctc alignment
|
3 years ago |
Hui Zhang
|
6ee67785f6
|
fix ctc alignment
|
3 years ago |
Hui Zhang
|
717fe1e4bd
|
Merge pull request #680 from PaddlePaddle/checkpoint
checkpoint refactor to save disk space
|
3 years ago |
Haoxin Ma
|
c0f7aac8fc
|
revise conf/*.yaml
|
3 years ago |
Haoxin Ma
|
08b6213bc8
|
fix private function
|
3 years ago |
Hui Zhang
|
7ec623f7ae
|
Merge branch 'develop' into align
|
3 years ago |
Haoxin Ma
|
6d92417edd
|
optimize the function
|
3 years ago |
Hui Zhang
|
9b3acddd5d
|
fix conf for new datapipe; u2 export inputspec
|
3 years ago |
Hui Zhang
|
9c0b6c5bb0
|
fix audio shape bug for audio len
|
3 years ago |
Haoxin Ma
|
16210c0587
|
fix bug
|
3 years ago |
Haoxin Ma
|
91e70a2857
|
multi gpus
|
3 years ago |
Haoxin Ma
|
3965dbc2c3
|
runtime.py
|
3 years ago |
Hui Zhang
|
90788b116d
|
more comment; fix datapipe of align
|
3 years ago |
Hui Zhang
|
1e2a5887aa
|
Merge branch 'develop' into align
|
3 years ago |
Haoxin Ma
|
340e622953
|
fix runtime and server
|
3 years ago |
Haoxin Ma
|
c753b9ddf2
|
fix runtime.py and server.py
|
3 years ago |
Haoxin Ma
|
d55e6b5a0a
|
revise from_pretrained function
|
3 years ago |
Haoxin Ma
|
8af2eb073a
|
revise config
|
3 years ago |
Haoxin Ma
|
68bcc46940
|
save best and test on tiny/s0
|
3 years ago |
Haoxin Ma
|
3652b87f33
|
fix
|
3 years ago |
Haoxin Ma
|
3a743f3717
|
fix pre-commit
|
3 years ago |
Haoxin Ma
|
089a8ed602
|
fix deepspeech2/model.py and deepspeech2/config.py
|
3 years ago |
Haoxin Ma
|
557427736e
|
move redundant params
|
3 years ago |
Haoxin Ma
|
698d7a9bdb
|
move batch_size, work_nums, shuffle_method, sortagrad to collator
|
3 years ago |
Haoxin Ma
|
89a00eabeb
|
revise deepspeech/exps/u2/model.py
|
3 years ago |
Haoxin Ma
|
6ee3033cc4
|
finish aishell/s0
|
3 years ago |
Haoxin Ma
|
7bae32f384
|
revise example/ting/s1
|
3 years ago |
Haoxin Ma
|
b9110af9d3
|
feat_dim, vocab_size
|
3 years ago |
Haoxin Ma
|
3855522ee3
|
config
|
3 years ago |
Haoxin Ma
|
a1c6ee5ca1
|
merge
|
3 years ago |
Haoxin Ma
|
3d5f294363
|
dataset
|
3 years ago |
Blank
|
875139ca04
|
Merge branch 'develop' into spec_aug
|
3 years ago |
Hui Zhang
|
1cd88d2619
|
Merge pull request #657 from PaddlePaddle/add_utt
add utt to datapipeline
|
3 years ago |
Haoxin Ma
|
2b51d612dd
|
delete _instance_reader_creator func in dataset
|
3 years ago |
Haoxin Ma
|
b4bda290aa
|
fix bugs
|
3 years ago |
Haoxin Ma
|
c706dfec2a
|
fix bug
|
3 years ago |
Haoxin Ma
|
279348d786
|
move process utt to collator
|
3 years ago |
Haoxin Ma
|
8781ab58cf
|
fix export and run.sh
|
3 years ago |
Haoxin Ma
|
a58b1cb30a
|
add result output
|
3 years ago |
Haoxin Ma
|
f3c9f32c9a
|
add utt to train and test 0607
|
3 years ago |
Haoxin Ma
|
c8368410e2
|
utt datapipeline
|
3 years ago |
Hui Zhang
|
69dfc2a5fa
|
fix mask for bool type; fix other
|
3 years ago |
Hui Zhang
|
4acaaba349
|
replace list zip by stack
|
4 years ago |
Hui Zhang
|
d05ae8eeb0
|
Merge branch 'develop' into align
|
4 years ago |
Hui Zhang
|
34689bd1df
|
add crf
|
4 years ago |
Hui Zhang
|
b3bc451328
|
remove sequnce_mask and change ds2 export audio shape to [B,T,D] (#639)
* remove sequnce_mask
* format
* fix ds2 export audio shape from B,D,T to B,T,D
|
4 years ago |
Hui Zhang
|
92381451fb
|
format
|
4 years ago |