Hui Zhang
|
ecbe785e47
|
remove ctc grad norm option
|
3 years ago |
huangyuxin
|
895a086fdd
|
rename the config.feat_size and the config.vocab.size to input_size and output_size
|
3 years ago |
huangyuxin
|
b6a466ceea
|
upload the demo audio_file
|
3 years ago |
huangyuxin
|
ef27a0e18a
|
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into dev
|
3 years ago |
Hui Zhang
|
396db4a56a
|
update librispeech asr1-2 result; add warpctc source link in ctc topic
|
3 years ago |
Hui Zhang
|
712de751cb
|
Merge pull request #1036 from zh794390558/nproc
[asr] nproc to ngpu
|
3 years ago |
Hui Zhang
|
fd15d0daf8
|
Merge pull request #1035 from zh794390558/dataset
[asr] dataset to root dir
|
3 years ago |
huangyuxin
|
357a6723e0
|
fix the audio_file location in run.sh
|
3 years ago |
Hui Zhang
|
fe83adfbcb
|
nproc to ngpu
|
3 years ago |
Hui Zhang
|
6151800d04
|
fix dataset dir in data.sh
|
3 years ago |
Hui Zhang
|
733b0ce29a
|
rename to result.md
|
3 years ago |
Hui Zhang
|
b119cfe06d
|
fix preprocess of libri asr2
|
3 years ago |
Jackwaterveg
|
04cfcd96ca
|
Merge pull request #1023 from zh794390558/dict
[asr] put vocab into data/lang_char
|
3 years ago |
Hui Zhang
|
cdeb5cf6b6
|
update librispeech transformer result
|
3 years ago |
Hui Zhang
|
4f54e36294
|
vocab into data/lang_char
|
3 years ago |
huangyuxin
|
8aebfeac81
|
fix the prc-commit
|
3 years ago |
Hui Zhang
|
2f4f744071
|
rename asr egs
|
3 years ago |
Hui Zhang
|
2ba3f00bbd
|
Merge branch 'develop' into datapipe
|
3 years ago |
Hui Zhang
|
0defc658e1
|
update aishell/librispeech transformer result; wenetspeech pretrain conformer result
|
3 years ago |
Hui Zhang
|
638b96bf07
|
check if cmvn_file in config for u2
|
3 years ago |
Hui Zhang
|
a87ba13d93
|
disable export for u2
|
3 years ago |
Hui Zhang
|
171fa353ee
|
refactor libri s2 conf
|
3 years ago |
Hui Zhang
|
bc4e2e4ee2
|
Merge pull request #982 from Jackwaterveg/develop
Optimizer the hips while downloading the LM
|
3 years ago |
huangyuxin
|
754c0b560b
|
optimizer the hips of downloading LM
|
3 years ago |
Hui Zhang
|
81598e6ff0
|
default gpu 0 for scripts
|
3 years ago |
Hui Zhang
|
9a71c091c5
|
remove debug info and format code
|
3 years ago |
Hui Zhang
|
8b0e344c69
|
fix logfbank using PCM16
|
3 years ago |
Hui Zhang
|
d62092ac28
|
fix specaug param
|
3 years ago |
Hui Zhang
|
44743622d4
|
filter example; cmvn stride and window int; libri/s1 conf
|
3 years ago |
Hui Zhang
|
69055698a2
|
transformer using batch data loader
|
3 years ago |
huangyuxin
|
d647cde870
|
change the lm dataset dir
|
3 years ago |
Hui Zhang
|
e2bcaee4f1
|
merge deepspeech, parakeet and text_processing into paddlespeech
|
3 years ago |
huangyuxin
|
d64f6e9ea5
|
Add the feature: caculating the perplexity of transformerLM
|
3 years ago |
huangyuxin
|
e66da76db9
|
fix the bug of chooing dataloader, remove the log of downloads lm, change the epoch in tiny
|
3 years ago |
Hui Zhang
|
0812a3df20
|
add more join ctc decode conf
|
3 years ago |
Hui Zhang
|
c89820e7b2
|
fix egs of transformer lm usage
|
3 years ago |
Hui Zhang
|
b878027c9a
|
format code
|
3 years ago |
Hui Zhang
|
b7bdaf6f8f
|
add lm conf and load
|
3 years ago |
Hui Zhang
|
8f869b4c1f
|
update gitignore
|
3 years ago |
Hui Zhang
|
a107b75bac
|
transform; librispeech/s2 data process ok
|
3 years ago |
Hui Zhang
|
614a004c37
|
update librispeech/s2 result
|
3 years ago |
Hui Zhang
|
a37cfbfb96
|
add fbank/pitch conf
|
3 years ago |
Hui Zhang
|
7509dc4056
|
update path and flac
|
3 years ago |
Hui Zhang
|
871fc5b70d
|
more utils to support kaldi/espnet data preocess
|
3 years ago |
Hui Zhang
|
c5f6692191
|
update lirbi s2 result
|
3 years ago |
Hui Zhang
|
12f788dd0e
|
Merge branch 'develop' into join_ctc
|
3 years ago |
Hui Zhang
|
7cfb3334e3
|
Merge pull request #927 from PaddlePaddle/nn_ctc
[asr] not change ctc grad norm manually
|
3 years ago |
Hui Zhang
|
dfd80b3aa2
|
recog into decoders, format code
|
3 years ago |
Hui Zhang
|
a4e27da64b
|
decoder with ctc prefix score
|
3 years ago |
Hui Zhang
|
7d54ee4d1d
|
ctc_grad_norm_type by null
|
3 years ago |
Hui Zhang
|
30499a7654
|
not change ctc grad manual
|
3 years ago |
Hui Zhang
|
190f4cc4bc
|
update u2 result; fix test.sh
|
3 years ago |
huangyuxin
|
b1a90d4d7a
|
add hub for s1 in aishell and librispeech
|
3 years ago |
Hui Zhang
|
8539689b15
|
u2 kaldi wer4p0
|
3 years ago |
Hui Zhang
|
f55267f2b3
|
fix img link; rsl format;
|
3 years ago |
Hui Zhang
|
50b2114b3b
|
fix error condition
|
3 years ago |
Hui Zhang
|
feaf71d468
|
u2 kaldi mutli process test with batchsize one
|
3 years ago |
Jackwaterveg
|
aaa87698c4
|
Merge pull request #906 from PaddlePaddle/rsl
update librispeech conformer result
|
3 years ago |
Hui Zhang
|
b34da366ee
|
update librispeech conformer result
|
3 years ago |
Hui Zhang
|
302afed42a
|
update librispeech conformer transformer config
|
3 years ago |
Jackwaterveg
|
20488c56bc
|
Merge pull request #885 from PaddlePaddle/exp
compute cmvn before build vocab
|
3 years ago |
Hui Zhang
|
b10af1688c
|
update librispeech transformer test w/o length filter of test clean
|
3 years ago |
Hui Zhang
|
13a4bee8be
|
using simple test for multi decode type, and gpu
|
3 years ago |
Hui Zhang
|
eef8847a82
|
compute cmvn before build vocab
|
3 years ago |
Hui Zhang
|
f5ec6e34c6
|
disable __pycache__
|
3 years ago |
Hui Zhang
|
b7b1bda34f
|
test refactor collator
|
3 years ago |
Hui Zhang
|
9abf03bb6b
|
fix libri s1 transformer config
|
3 years ago |
Hui Zhang
|
8e16315ada
|
librispeech s1 support multi process decode and sclite
|
3 years ago |
Hui Zhang
|
20178e0e09
|
librispeech s1 support sclite and multi process decode
|
3 years ago |
Hui Zhang
|
9abe33b4bd
|
add score_sclite
|
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
|
80eb6b7f01
|
fix espnet kaldi libri s2 config
|
3 years ago |
Hui Zhang
|
15d26cc4ad
|
update u2 transformer config
|
3 years ago |
Hui Zhang
|
5fdda953b9
|
add op profiling
|
3 years ago |
Hui Zhang
|
ec76df6cbc
|
do not set seed since break model covergence, aishell s0 seed 10086 test ok
|
3 years ago |
Hui Zhang
|
28a0a64153
|
fix train.sh
|
3 years ago |
Hui Zhang
|
890a28f9bf
|
add more ctc conf
|
3 years ago |
Hui Zhang
|
41ed7a184c
|
add ctc conf
|
3 years ago |
Hui Zhang
|
1a8c5278a1
|
export ctc grad norm config
|
3 years ago |
Hui Zhang
|
7e136d0893
|
support no_sync for backward; ds support accum grad
|
3 years ago |
Hui Zhang
|
184d30dd9c
|
relase librispeech audio max len to 30 second
|
3 years ago |
Hui Zhang
|
d028c8416d
|
fix recipe train and avg shell
|
3 years ago |
huangyuxin
|
04d9db199f
|
add blank_id parameter
|
3 years ago |
Hui Zhang
|
d1db859657
|
fix dataloader pickle bugs
|
3 years ago |
huangyuxin
|
40466ef669
|
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into ds2_online
|
3 years ago |
Hui Zhang
|
715e90a9df
|
fix librispeech s0 specaug
|
3 years ago |
huangyuxin
|
b3d27e4bbb
|
merge the develop
|
3 years ago |
huangyuxin
|
2d3b2aed05
|
add seed in argparse
|
3 years ago |
Hui Zhang
|
561d5cf085
|
refactor feature, dict and argument for new config format
|
3 years ago |
Hui Zhang
|
aab02997f9
|
fix specaug config
|
3 years ago |
Hui Zhang
|
50f10f37ae
|
support replace with mean by aug
|
3 years ago |
Hui Zhang
|
c09b0e8940
|
fix specaug
|
3 years ago |
Hui Zhang
|
9dace62581
|
fix augmentation
|
3 years ago |
Hui Zhang
|
ab23eb5710
|
fix for kaldi
|
3 years ago |
Hui Zhang
|
f05f367cc5
|
Merge pull request #756 from PaddlePaddle/filter
test w/ all example & fix ctc api & add new io
|
3 years ago |
Hui Zhang
|
7d133368e5
|
fix bugs
|
3 years ago |
Hui Zhang
|
7b649af8d7
|
add batchfy
|
3 years ago |
Hui Zhang
|
e00567bb84
|
more result
|
3 years ago |
Hui Zhang
|
99dfe04515
|
test w/ all example
|
3 years ago |