8c0923b865
update gitignore; add gigaspeech
3 years ago
e106f243b4
dump dataset metadata
3 years ago
9e99f99b3c
add thchs30, aidatatang;
3 years ago
b8f190c12c
add thchs30 dataset
3 years ago
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
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
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
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.
3 years ago
759b2e0b2d
fix ds2 default config
3 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
3 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
3 years ago
1b373bfcd7
refactor g2p egs ( #630 )
...
* refactor g2p egs
* add sha-bone; remove avg.sh from egs;
3 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
3 years ago
0a7958b3f1
add tarball utils ( #626 )
3 years ago
37c5324138
fix result; add feature list
3 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
3 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
3 years ago
d777edc605
ctc decoding weight 0.5 ( #614 )
...
* ctc decoding weight 0.5
* tiny decoding conf
* more label of mergify
* format doc
3 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
3 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
3 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
3 years ago
258307df9b
fix egs bugs ( #552 )
...
* fix egs
* fix log
3 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
Hui Zhang
Haoxin Ma
chenfeiyu