9b3acddd5d
fix conf for new datapipe; u2 export inputspec
3 years ago
f8d52e598f
Merge branch 'develop' into rsl
3 years ago
03e6952501
more detial of result
3 years ago
718bd30765
Merge pull request #688 from PaddlePaddle/ds2_fix
...
fix conf for ds2
3 years ago
91e70a2857
multi gpus
3 years ago
019ae4b35c
fix conf for ds2
3 years ago
4b80b172d3
add model params
3 years ago
133a522fbb
ds2 default using 4gpu; new result of ds2
3 years ago
8af2eb073a
revise config
3 years ago
68bcc46940
save best and test on tiny/s0
3 years ago
68149cb9a7
fix config for new datapipeline
3 years ago
5a3a9e1f50
fix chunk default config; tarball ckpt prfix dir;
3 years ago
8c1bf1a730
fix ds2 conf for new data pipeline
3 years ago
557427736e
move redundant params
3 years ago
698d7a9bdb
move batch_size, work_nums, shuffle_method, sortagrad to collator
3 years ago
6ee3033cc4
finish aishell/s0
3 years ago
7bae32f384
revise example/ting/s1
3 years ago
b9110af9d3
feat_dim, vocab_size
3 years ago
875139ca04
Merge branch 'develop' into spec_aug
3 years ago
1cd88d2619
Merge pull request #657 from PaddlePaddle/add_utt
...
add utt to datapipeline
3 years ago
b4bda290aa
fix bugs
3 years ago
255a6f004e
result with specaug
3 years ago
279348d786
move process utt to collator
3 years ago
8781ab58cf
fix export and run.sh
3 years ago
a58b1cb30a
add result output
3 years ago
9bb1806246
fix clip conf
3 years ago
b3d23e6af3
add stream conf
3 years ago
ae92fa7498
format code
3 years ago
7779f33e74
add text normalization example
3 years ago
c8368410e2
utt datapipeline
3 years ago
69dfc2a5fa
fix mask for bool type; fix other
3 years ago
34689bd1df
add crf
3 years ago
de780a0c8a
add libri ds2 exp result
3 years ago
4c3c5546e7
1. use space as separator;
...
2. add docstring for some functions.
4 years ago
759b2e0b2d
fix ds2 default config
4 years ago
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
749a113037
add Cedict egs & pypinyin using jieba as wordseg & phkit using local pypinyin package ( #637 )
...
* down and parse cedict
* remove useless
* using third party python pinyin
* jieba as default wordseg
* remove useless
* remove pinyin dict
* using jieba.lcut
* remove doc of cedict egs
* add fan2jian test
* add description for say_digit
4 years ago
1b373bfcd7
refactor g2p egs ( #630 )
...
* refactor g2p egs
* add sha-bone; remove avg.sh from egs;
4 years ago
075635d2b4
add a g2p example ( #623 )
...
* add an example to convert transcription to pinyin with pypinyin and jieba
* format code
* 1. remove script for data downloading, since Baker dataset is not easily downloaded via terminal;
2. remove pypinyin as an extra requirement; it is alreay required by the main project;
3. clean code.
* change output format
4 years ago
0a7958b3f1
add tarball utils ( #626 )
4 years ago
37c5324138
fix result; add feature list
4 years ago
0a3a840bee
more decoding method ( #618 )
...
* more decoding method
* all decode method test scripts; result readme
* exp libri confi
* parallel data scripts; more mask test; need pybind11 repo
* speed perturb config
* libri conf test set
4 years ago
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
4 years ago
d777edc605
ctc decoding weight 0.5 ( #614 )
...
* ctc decoding weight 0.5
* tiny decoding conf
* more label of mergify
* format doc
4 years ago
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
4 years ago
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
4 years ago
e0a87a5ab1
batch average ctc loss ( #567 )
...
* when loss div batchsize, change lr, more epoch, loss can reduce more and cer lower than before
* since loss reduce more when loss div batchsize, less lm alpha can be better.
* less lm alpha, more cer reduce
* alpha 2.2, cer 0.077478
* alpha 1.9, cer 0.077249
* large librispeech lr for batch_average ctc loss
* since loss reduce and model more confidence, then less lm alpha
4 years ago
258307df9b
fix egs bugs ( #552 )
...
* fix egs
* fix log
4 years ago
1539f3e0a3
Refactor CTC module, add embedding and fix log ( #549 )
...
* add acts, refactor ctc, add pos embed
* fix export, dataloader time log
* fix egs
* fix libri readme
4 years ago
19e0f2ac46
Fix doc format ( #546 )
4 years ago
57ed5cd2e0
Fix Doc ( #544 )
4 years ago
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
141109b49d
update aishell egs
4 years ago
7357e52188
fix egs
4 years ago
9cfca9fc40
fix dataset dir
4 years ago
123d7a6f3f
refactor egs
4 years ago
ba7cf0782e
add copyright
4 years ago
75c8018eab
refactor tiny egs
4 years ago
126677a35c
support py3
4 years ago
b4d3eeadda
change the default configuration in infer.py and test.py
5 years ago
d89c3a48a7
unify api to 1.6 version and fix some problems
5 years ago
d74f4ff3f5
update deepspeech to fluid api
5 years ago
3ecf1ad4f5
Decouple ext scorer init & inference & decoding for the convenience of tuning
7 years ago
6e4f246517
retune hyper-parameters for librispeech model
7 years ago
c786b18265
Uncomment model downloading lines
7 years ago
938685baa0
Add infer & test script for baidu_en8k model
7 years ago
24cb1866a8
Adapt settings for Aishell example.
7 years ago
9800d14956
fix the data path in the librispeech example
7 years ago
528895cf26
fix the model path in the tiny example
7 years ago
edaed68f33
Involve dev dataset to build vocabulary in the aishell example
7 years ago
d58dd5fe72
Release BaiduEn8k model and prepare demo example.
7 years ago
ad08dd963a
supply param cutoff_top_n in several scripts of DS2
7 years ago
9ac15f8bd8
Merge pull request #363 from xinghai-sun/default_value
...
Reset default value of batch_size, num_proc_data and fix an invalid url for DS2.
7 years ago
86811af7a3
Reset default value of batch_size, nun_proc_data and fix an invalid url for DS2.
7 years ago
758e9887ca
Bug fix for librispeech/run_train.sh.
7 years ago
be1fbc68a1
Set process daemon property and reset default value of num_proc_data arguments.
7 years ago
2c63f3413f
convert decoding results to unicode in DS2
7 years ago
8dcf1d5667
fix bugs in preparing data scripts
7 years ago
3663ba57d0
make *.sh files more robust in DS2
7 years ago
6cac602bc5
Merge pull request #194 from kuke/improve_tuning_dev
...
Improve params tuning strategy for CTC beam search decoder
7 years ago
e6e7b13222
remove the log praser in tuning script
7 years ago
4c64841c16
add tuning script & enable ploting error surface
7 years ago
0a5f123764
Add inference scripts.
7 years ago
a235b3532d
Add test script.
7 years ago
7b9385899b
Add training script.
7 years ago
e9a42044f5
Add data preparing for Aishell.
7 years ago
3615b44ffd
Merge branch 'develop' of upstream into ctc_decoder_deploy
7 years ago
7f45752a13
Add profile.sh script for multi-gpu profiling.
7 years ago
acf2072ed4
Merge branch 'develop' of upstream into ctc_decoder_deploy
7 years ago
1b206b3390
fix bugs for model.py and demo_server.py.
7 years ago
a24d0138d9
adjust scorer's init & add logging for scorer & separate long functions
7 years ago
7e093ed1a3
expose param cutoff_top_n
7 years ago
a18e6a7eda
refine by following review comments
7 years ago
cd635cf6f3
Release librispeech model url.
7 years ago
f2120bb5dc
adapt to the new structure
7 years ago
ac56a2f249
Update READMD.md and other details by following reviewers comments.
7 years ago
87453365b2
Update REAME.md for DS2.
7 years ago
e11b735de5
Update examples scripts and REAME.md for DS2.
7 years ago
ae7ef7929a
Rename some folders and update examples.
7 years ago
a00a436b52
Rewrite README.md doc (50%) and correct some bugs.
7 years ago
8ec4a96523
resolve conflicts in model.py
7 years ago
7d0458c7f7
adapt to the new folder structure of DS2
7 years ago
69e0d86ddb
fix wrong path in prepare.sh
7 years ago
0bbb9c3ee2
Re-organize folder structure and hierarchy for DS2.
7 years ago
Hui Zhang
Haoxin Ma
chenfeiyu
lfchener
Yibing Liu
yangyaming
Xinghai Sun
Yibing Liu
Luo Tao