Hui Zhang
d395c2b8e3
jsonlines reade manifest file
3 years ago
Hui Zhang
7554b6107a
using visualdl; fix read_manifest
3 years ago
Junkun Chen
2301fed1b4
Merge branch 'PaddlePaddle:develop' into develop
3 years ago
TianYuan
79060e20e3
Update pack_model.sh
3 years ago
Junkun
0cc81a52cd
update format
3 years ago
Junkun
ea35558ee0
add utils
3 years ago
Hui Zhang
02c7ef3198
format data support multi output
3 years ago
Hui Zhang
f89f99fe4a
update pack model tool
3 years ago
Hui Zhang
e79e00a6b2
pack model
3 years ago
Hui Zhang
fb853167d3
format code
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
Hui Zhang
e2bcaee4f1
merge deepspeech, parakeet and text_processing into paddlespeech
3 years ago
Hui Zhang
b878027c9a
format code
3 years ago
Hui Zhang
a107b75bac
transform; librispeech/s2 data process ok
3 years ago
Hui Zhang
6569ce123d
lm embed and format code
3 years ago
Hui Zhang
871fc5b70d
more utils to support kaldi/espnet data preocess
3 years ago
Hui Zhang
e4ecfb22fd
format code
3 years ago
Hui Zhang
ee6446a3aa
avg model dump val loss mean
3 years ago
Hui Zhang
fa5531c03e
Merge pull request #908 from PaddlePaddle/speech
...
[TTS] merge parakeet repo into deepspeech
3 years ago
Hui Zhang
b079577e08
merge parakeet repo into deepspeech
3 years ago
Hui Zhang
feaf71d468
u2 kaldi mutli process test with batchsize one
3 years ago
Hui Zhang
e7b0f5ed4a
reader default type is mat, sound need explicitlyc specify
3 years ago
Hui Zhang
b7b1bda34f
test refactor collator
3 years ago
huangyuxin
f6c9976189
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into release_model
3 years ago
Hui Zhang
30563981f0
replace space when build vocab
3 years ago
Hui Zhang
4c098a0f33
explit space as <space>
3 years ago
huangyuxin
285e0c9cad
merge the change
3 years ago
Hui Zhang
8e16315ada
librispeech s1 support multi process decode and sclite
3 years ago
Hui Zhang
33b8790252
refactor avg_model; fix set_value not support start==end
3 years ago
Hui Zhang
9d5eb74066
fix decode json file
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
huangyuxin
264bba760b
fix the bug: read space as unk
3 years ago
Hui Zhang
80eb6b7f01
fix espnet kaldi libri s2 config
3 years ago
Hui Zhang
438e1bd34f
add benmark scripts
3 years ago
Hui Zhang
f54dc983b6
using bw rnn in ds2
3 years ago
Hui Zhang
341038b626
ds2 offline cer 6p4287
3 years ago
Junkun
9d05a749e2
script for TED-En-Zh translation
3 years ago
Hui Zhang
571b13c53f
add dur utils
3 years ago
Hui Zhang
fd8a4ec179
Merge pull request #729 from PaddlePaddle/fst
...
TLG graph
3 years ago
Hui Zhang
ab5411ec16
Merge pull request #698 from yt605155624/thchs30_MFA
...
Thchs30 mfa
3 years ago
Hui Zhang
104743cccc
TLG build pass
3 years ago
Hui Zhang
f5369abdbe
add TLG utils
3 years ago
Hui Zhang
8998f4c24d
add timit
3 years ago
TianYuan
00017301c6
restructure thchs30/a0
3 years ago
Hui Zhang
3c6eea077b
cp dir when it exits
3 years ago
Hui Zhang
1b84f21ccf
fix miss match
3 years ago
Hui Zhang
5a3a9e1f50
fix chunk default config; tarball ckpt prfix dir;
3 years ago
Hui Zhang
1b373bfcd7
refactor g2p egs ( #630 )
...
* refactor g2p egs
* add sha-bone; remove avg.sh from egs;
3 years ago
Hui Zhang
0a7958b3f1
add tarball utils ( #626 )
3 years ago
Hui Zhang
295f8bdad5
train ds2 model ( #622 )
...
* default cmvn compute config; more log of grad clip; diff ds2 cmvn compute and conf; ds2 lr step by epoch;
* fix ds2 config
* fix install and egs link
* sox speed pertrub shape (T, C), float64, process using int32
* fix libri ds2 scripts; add ngram and spm doc
* aishell ds2 cer7.86
* fix ds2 result
3 years ago
Hui Zhang
538bf271eb
chinese char/word ngram lm ( #613 )
...
* add ngram lm egs
* add zhon repo
* install kenlm, zhon
* format
* add chinese_text_normalization repo
* add ngram lm egs
3 years ago
Hui Zhang
71e046b0ba
E2E/Streaming Transformer/Conformer ASR ( #578 )
...
* add cmvn and label smoothing loss layer
* add layer for transformer
* add glu and conformer conv
* add torch compatiable hack, mask funcs
* not hack size since it exists
* add test; attention
* add attention, common utils, hack paddle
* add audio utils
* conformer batch padding mask bug fix #223
* fix typo, python infer fix rnn mem opt name error and batchnorm1d, will be available at 2.0.2
* fix ci
* fix ci
* add encoder
* refactor egs
* add decoder
* refactor ctc, add ctc align, refactor ckpt, add warmup lr scheduler, cmvn utils
* refactor docs
* add fix
* fix readme
* fix bugs, refactor collator, add pad_sequence, fix ckpt bugs
* fix docstring
* refactor data feed order
* add u2 model
* refactor cmvn, test
* add utils
* add u2 config
* fix bugs
* fix bugs
* fix autograd maybe has problem when using inplace operation
* refactor data, build vocab; add format data
* fix text featurizer
* refactor build vocab
* add fbank, refactor feature of speech
* refactor audio feat
* refactor data preprare
* refactor data
* model init from config
* add u2 bins
* flake8
* can train
* fix bugs, add coverage, add scripts
* test can run
* fix data
* speed perturb with sox
* add spec aug
* fix for train
* fix train logitc
* fix logger
* log valid loss, time dataset process
* using np for speed perturb, remove some debug log of grad clip
* fix logger
* fix build vocab
* fix logger name
* using module logger as default
* fix
* fix install
* reorder imports
* fix board logger
* fix logger
* kaldi fbank and mfcc
* fix cmvn and print prarams
* fix add_eos_sos and cmvn
* fix cmvn compute
* fix logger and cmvn
* fix subsampling, label smoothing loss, remove useless
* add notebook test
* fix log
* fix tb logger
* multi gpu valid
* fix log
* fix log
* fix config
* fix compute cmvn, need paddle 2.1
* add cmvn notebook
* fix layer tools
* fix compute cmvn
* add rtf
* fix decoding
* fix layer tools
* fix log, add avg script
* more avg and test info
* fix dataset pickle problem; using 2.1 paddle; num_workers can > 0; ckpt save in exp dir;fix setup.sh;
* add vimrc
* refactor tiny script, add transformer and stream conf
* spm demo; librisppech scripts and confs
* fix log
* add librispeech scripts
* refactor data pipe; fix conf; fix u2 default params
* fix bugs
* refactor aishell scripts
* fix test
* fix cmvn
* fix s0 scripts
* fix ds2 scripts and bugs
* fix dev & test dataset filter
* fix dataset filter
* filter dev
* fix ckpt path
* filter test, since librispeech will cause OOM, but all test wer will be worse, since mismatch train with test
* add comment
* add syllable doc
* fix ds2 configs
* add doc
* add pypinyin tools
* fix decoder using blank_id=0
* mmseg with pybind11
* format code
3 years ago
Hui Zhang
d4e84f9b9d
fix doc link and enhance install ( #570 )
...
* fix doc link
* fix install
* fix install doc
* fix typo
* fix lm doc
3 years ago
Hui Zhang
d7e753546a
Support paddle 2.x ( #538 )
...
* 2.x model
* model test pass
* fix data
* fix soundfile with flac support
* one thread dataloader test pass
* export feasture size
add trainer and utils
add setup model and dataloader
update travis using Bionic dist
* add venv; test under venv
* fix unittest; train and valid
* add train and config
* add config and train script
* fix ctc cuda memcopy error
* fix imports
* fix train valid log
* fix dataset batch shuffle shift start from 1
fix rank_zero_only decreator error
close tensorboard when train over
add decoding config and code
* test process can run
* test with decoding
* test and infer with decoding
* fix infer
* fix ctc loss
lr schedule
sortagrad
logger
* aishell egs
* refactor train
add aishell egs
* fix dataset batch shuffle and add batch sampler log
print model parameter
* fix model and ctc
* sequence_mask make all inputs zeros, which cause grad be zero, this is a bug of LessThanOp
add grad clip by global norm
add model train test notebook
* ctc loss
remove run prefix
using ord value as text id
* using unk when training
compute_loss need text ids
ord id using in test mode, which compute wer/cer
* fix tester
* add lr_deacy
refactor code
* fix tools
* fix ci
add tune
fix gru model bugs
add dataset and model test
* fix decoding
* refactor repo
fix decoding
* fix musan and rir dataset
* refactor io, loss, conv, rnn, gradclip, model, utils
* fix ci and import
* refactor model
add export jit model
* add deploy bin and test it
* rm uselss egs
* add layer tools
* refactor socket server
new model from pretrain
* remve useless
* fix instability loss and grad nan or inf for librispeech training
* fix sampler
* fix libri train.sh
* fix doc
* add license on cpp
* fix doc
* fix libri script
* fix install
* clip 5 wer 7.39, clip 400 wer 7.54, 1.8 clip 400 baseline 7.49
4 years ago
Hui Zhang
ba7cf0782e
add copyright
4 years ago
Hui Zhang
126677a35c
support py3
4 years ago
lfchener
d74f4ff3f5
update deepspeech to fluid api
5 years ago
yangyaming
0f9b3ebf0e
Move exception throwing logic to cer and wer.
7 years ago
yangyaming
a8793039f3
Expose edit distance for error_rate.py
7 years ago
Xinghai Sun
c3710b7f52
Add wget return check.
7 years ago
Xinghai Sun
cd635cf6f3
Release librispeech model url.
7 years ago
Xinghai Sun
e11b735de5
Update examples scripts and REAME.md for DS2.
7 years ago
Xinghai Sun
d776ce9bd7
Fix import errors in unitests.
7 years ago
Xinghai Sun
5623b09868
Move decoder.py to models and re-arrange unitests.
7 years ago
Xinghai Sun
0bbb9c3ee2
Re-organize folder structure and hierarchy for DS2.
7 years ago