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
|
|
|
|
# GBK/GB 18030 PUA 映射
|
|
|
|
|
|
# 详见：https://zh.wikipedia.org/wiki/GB_18030#PUA
|
|
|
|
|
|
# U+E815: # Unihan: U+2E81 ⺁
|
|
|
|
|
|
U+E816: zuǒ # Unihan: U+20087 𠂇
|
|
|
|
|
|
# U+E817: # Unihan: U+20089 𠂉
|
|
|
|
|
|
U+E818: gǔn # Unihan: U+200CC 𠃌
|
|
|
|
|
|
# U+E819: # Unihan: U+2E84 ⺄
|
|
|
|
|
|
U+E81A: zhòu,zhū # Unihan: U+3473 㑳
|
|
|
|
|
|
U+E81B: zhòu # Unihan: U+3447 㑇
|
|
|
|
|
|
# U+E81C: # Unihan: U+2E88 ⺈
|
|
|
|
|
|
# U+E81D: # Unihan: U+2E8B ⺋
|
|
|
|
|
|
# U+E81E: # Unihan: U+9FB4 龴
|
|
|
|
|
|
U+E81F: wāi # Unihan: U+359E 㖞
|
|
|
|
|
|
U+E820: hǎn # Unihan: U+361A 㘚
|
|
|
|
|
|
U+E821: hǎn # Unihan: U+360E 㘎
|
|
|
|
|
|
# U+E822: # Unihan: U+2E8C ⺌
|
|
|
|
|
|
# U+E823: # Unihan: U+2E97 ⺗
|
|
|
|
|
|
U+E824: zhòu,chǎo # Unihan: U+396E 㥮
|
|
|
|
|
|
U+E825: zhòu # Unihan: U+3918 㤘
|
|
|
|
|
|
# U+E826: # Unihan: U+9FB5 龵
|
|
|
|
|
|
U+E827: gāng # Unihan: U+39CF 㧏
|
|
|
|
|
|
U+E828: kuǎi # Unihan: U+39DF 㧟
|
|
|
|
|
|
U+E829: sǒng # Unihan: U+3A73 㩳
|
|
|
|
|
|
U+E82A: sǒng # Unihan: U+39D0 㧐
|
|
|
|
|
|
# U+E82B: # Unihan: U+9FB6 龶
|
|
|
|
|
|
# U+E82C: # Unihan: U+9FB7 龷
|
|
|
|
|
|
U+E82D: gāng # Unihan: U+3B4E 㭎
|
|
|
|
|
|
U+E82E: kuài # Unihan: U+3C6E 㱮
|
|
|
|
|
|
U+E82F: tà # Unihan: U+3CE0 㳠
|
|
|
|
|
|
# U+E830: # Unihan: U+2EA7 ⺧
|
|
|
|
|
|
U+E831: pěng # Unihan: U+215D7 𡗗
|
|
|
|
|
|
# U+E832: # Unihan: U+9FB8 龸
|
|
|
|
|
|
# U+E833: # Unihan: U+2EAA ⺪
|
|
|
|
|
|
U+E834: lōu # Unihan: U+4056 䁖
|
|
|
|
|
|
U+E835: cǎn # Unihan: U+415F 䅟
|
|
|
|
|
|
# U+E836: # Unihan: U+2EAE ⺮
|
|
|
|
|
|
U+E837: chōu,chóu # Unihan: U+4337 䌷
|
|
|
|
|
|
# U+E838: # Unihan: U+2EB3 ⺳
|
|
|
|
|
|
# U+E839: # Unihan: U+2EB6 ⺶
|
|
|
|
|
|
# U+E83A: # Unihan: U+2EB7 ⺷
|
|
|
|
|
|
U+E83B: zāi # Unihan: U+2298F 𢦏
|
|
|
|
|
|
U+E83C: bà,bēi # Unihan: U+43B1 䎱
|
|
|
|
|
|
U+E83D: bà # Unihan: U+43AC 䎬
|
|
|
|
|
|
# U+E83E: # Unihan: U+2EBB ⺻
|
|
|
|
|
|
U+E83F: zhuān # Unihan: U+43DD 䏝
|
|
|
|
|
|
U+E840: qióng # Unihan: U+44D6 䓖
|
|
|
|
|
|
U+E841: kuì,huì # Unihan: U+4661 䙡
|
|
|
|
|
|
U+E842: kuì # Unihan: U+464C 䙌
|
|
|
|
|
|
# U+E843: # Unihan: U+9FB9 龹
|
|
|
|
|
|
U+E844: xīn # Unihan: U+4723 䜣
|
|
|
|
|
|
U+E845: yàn # Unihan: U+4729 䜩
|
|
|
|
|
|
U+E846: jìng,qíng # Unihan: U+477C 䝼
|
|
|
|
|
|
U+E847: qíng # Unihan: U+478D 䞍
|
|
|
|
|
|
# U+E848: # Unihan: U+2ECA ⻊
|
|
|
|
|
|
U+E849: shàn # Unihan: U+4947 䥇
|
|
|
|
|
|
U+E84A: yé # Unihan: U+497A 䥺
|
|
|
|
|
|
U+E84B: pō # Unihan: U+497D 䥽
|
|
|
|
|
|
U+E84C: shàn # Unihan: U+4982 䦂
|
|
|
|
|
|
U+E84D: zhuō # Unihan: U+4983 䦃
|
|
|
|
|
|
U+E84E: shàn # Unihan: U+4985 䦅
|
|
|
|
|
|
U+E84F: jué # Unihan: U+4986 䦆
|
|
|
|
|
|
U+E850: wěn,chuài # Unihan: U+499F 䦟
|
|
|
|
|
|
U+E851: zhèng # Unihan: U+499B 䦛
|
|
|
|
|
|
U+E852: chuài # Unihan: U+49B7 䦷
|
|
|
|
|
|
U+E853: zhèng # Unihan: U+49B6 䦶
|
|
|
|
|
|
# U+E854: # Unihan: U+9FBA 龺
|
|
|
|
|
|
U+E855: yíng # Unihan: U+241FE 𤇾
|
|
|
|
|
|
U+E856: yú # Unihan: U+4CA3 䲣
|
|
|
|
|
|
U+E857: yìn # Unihan: U+4C9F 䲟
|
|
|
|
|
|
U+E858: chūn # Unihan: U+4CA0 䲠
|
|
|
|
|
|
U+E859: qiū # Unihan: U+4CA1 䲡
|
|
|
|
|
|
U+E85A: yú # Unihan: U+4C77 䱷
|
|
|
|
|
|
U+E85B: téng # Unihan: U+4CA2 䲢
|
|
|
|
|
|
U+E85C: shī # Unihan: U+4D13 䴓
|
|
|
|
|
|
U+E85D: jiāo # Unihan: U+4D14 䴔
|
|
|
|
|
|
U+E85E: liè # Unihan: U+4D15 䴕
|
|
|
|
|
|
U+E85F: jīng # Unihan: U+4D16 䴖
|
|
|
|
|
|
U+E860: jú # Unihan: U+4D17 䴗
|
|
|
|
|
|
U+E861: tī # Unihan: U+4D18 䴘
|
|
|
|
|
|
U+E862: pì # Unihan: U+4D19 䴙
|
|
|
|
|
|
U+E863: yǎn # Unihan: U+4DAE 䶮
|
|
|
|
|
|
# U+E864: # Unihan: U+9FBB 龻
|
