6745e9dd6b
fix dp init
2 years ago
795eb7bd10
format paddlespeech with pre-commit ( #2331 )
2 years ago
ed80b0e2c3
fix multigpu training test=asr
2 years ago
733ec7f2bc
fix conformer multi-gpu training test=asr
2 years ago
05bc258833
update docstring
2 years ago
812d80ab1c
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into u2_export
2 years ago
e5a6c243f1
fix jit save for conformer
2 years ago
4e7106d9e2
Support dy2st
2 years ago
ef37f73a01
fix cnn cache dy2st shape
2 years ago
e6ac8881f1
Fix comments
2 years ago
75997d8277
merge
2 years ago
e81849277e
att cache for streaming asr
2 years ago
fb40602d94
refactor attention cache
2 years ago
05d41523ad
Merge branch 'develop' into webdataset
2 years ago
92d1d08b9a
fix scripts
2 years ago
bc93bffbb4
replace logger.info with logger.debug in cli, change default log level to INFO
2 years ago
dfdf450b22
fix #2013 ; and format
2 years ago
47dd61e5b2
refactor ds2, cli, server
2 years ago
aa3d151d1d
Merge pull request #1994 from Jackwaterveg/develop
...
[ASR] not install ctc on win
2 years ago
10819e0fa2
not install ctc on win, test=asr
2 years ago
42fba661c9
more detail of copyright
2 years ago
b23bde8ec5
tensor.shape => paddle.shape(tensor)
2 years ago
4c09927f61
fix
2 years ago
e1888f9ae6
remove size,test=asr
2 years ago
c7d9b11529
format
2 years ago
9c03280ca6
remove debug info, test=doc
2 years ago
d21ccd0287
add conformer online server, test=doc
2 years ago
ca860e3d2f
supplement note
2 years ago
6da8465f14
add dist_sampler args, test=asr
3 years ago
a4f5a68074
fix some format, test=asr
3 years ago
d53e1163a6
update the code, test=asr
3 years ago
ab16d8ce3c
change default initializer to kaiming_uniform, test=asr
3 years ago
75098698d8
format,test=doc
3 years ago
f49cf838a8
Update u2.py ( #1378 )
3 years ago
d7222c0453
[ASR] Support CTC decoder online ( #821 )
...
* fix the destructer problem for prefixes
* unified offline and online in ctcdecoders, test=asr
* rename swig_decoders to paddlespeech_ctcdecoders, test=asr
* add reset_stage for ctcdecoder
* fix some problems
* fix ctconline
* fix a bug
* fix the format
* fix 1xt2x
3 years ago
44408e5211
sync the variable name to others
3 years ago
f866059b74
config and formalize
3 years ago
43aad7a018
beam search with optimality guarantees
3 years ago
ddf184be60
fix some typos
3 years ago
07d457859d
use pre-commit, test=doc_fix
3 years ago
3e2cc898cb
remove default cfg and fix some bugs,test=asr
3 years ago
c907a8deda
change all recipes
3 years ago
d852aee2ff
[asr] logfbank with dither ( #1179 )
...
* fix logfbank dither
* format
3 years ago
0151f2463f
fix bug of pad_sequence in u2,test=asr ( #1153 )
3 years ago
5b446f6321
[Config]clear the u2 decode config for asr ( #1107 )
...
* clear the u2 decode config
* rename the vocab_filepath and cmvn_path
3 years ago
51d7a07c6d
format and fix pre-commit ( #1120 )
3 years ago
b1c80c45e0
remove ctc grad norm type in config
3 years ago
cea5ffe0e4
refactor the code
3 years ago
ed12db61a6
Separate the ctcdecoders
3 years ago
895a086fdd
rename the config.feat_size and the config.vocab.size to input_size and output_size
3 years ago
2ba3f00bbd
Merge branch 'develop' into datapipe
3 years ago
0defc658e1
update aishell/librispeech transformer result; wenetspeech pretrain conformer result
3 years ago
638b96bf07
check if cmvn_file in config for u2
3 years ago
7c8843448c
add word reward into beam search.
3 years ago
000fac53fe
Merge pull request #966 from Jackwaterveg/dev
...
change the lm dataset dir, add the 'LM_BIN_DIR' in s2 path.sh
3 years ago
9cdd2643b1
fix bug for batch dataloader using
3 years ago
d647cde870
change the lm dataset dir
3 years ago
38cf56295a
fix reference format
3 years ago
c463a00f81
add reference code license
3 years ago
e2bcaee4f1
merge deepspeech, parakeet and text_processing into paddlespeech
3 years ago
tianhao zhang
TianYuan
Hui Zhang
0x45f
huangyuxin
xiongxinlei
Jackwaterveg
Junkun
billishyahao