Hui Zhang
|
b1c80c45e0
|
remove ctc grad norm type in config
|
3 years ago |
|
Hui Zhang
|
aa04e2652f
|
rm uesless comment
|
3 years ago |
|
Hui Zhang
|
7992aa6623
|
update librispeech asr1 transformer result
|
3 years ago |
|
Hui Zhang
|
2bbc4db508
|
fix install
|
3 years ago |
|
Hui Zhang
|
581a545c69
|
Update RESULTS.md
fix table header
|
3 years ago |
|
Hui Zhang
|
27087de5e9
|
update librispeech asr1 transformer result
|
3 years ago |
|
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 |
