72 Commits (c81743403ad2b3bb62c42c008221914cf2de0897)

Author	SHA1	Message	Date
huangyuxin	61fe292c47	Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into ds2_online	3 years ago
huangyuxin	718ae52e3f	add from_config function to ds2_oneline and ds2	3 years ago
Hui Zhang	4c0ee8d354	fix conf and readme	3 years ago
huangyuxin	7a3d164122	fix the bidirect rnn, add deepspeech2.yaml for aishell, tiny, librispeech	3 years ago
Hui Zhang	895330bad3	refactor ted en zh script; fix MAIN_ROOT path	3 years ago
huangyuxin	61d8540451	reconstruct the export function and the run.sh in aishell and librispeech	3 years ago
huangyuxin	156e324bbb	注释了sever.sh的17-21行	3 years ago
Hui Zhang	6c4e1361be	fix chunk mode test script	3 years ago
Hui Zhang	a486f6e618	Merge pull request #730 from PaddlePaddle/doc ... refactor egs readme	3 years ago
Hui Zhang	a546b96f85	refactor egs readme	3 years ago
Hui Zhang	3e5f587537	fix path.sh	3 years ago
Hui Zhang	40dcbbde26	add srilm install	3 years ago
Hui Zhang	104743cccc	TLG build pass	3 years ago
Hui Zhang	f5369abdbe	add TLG utils	3 years ago
Hui Zhang	8c9e142492	fix kenlm install; librispeech s0 aug	3 years ago
Hui Zhang	007746bf7f	fix sha bone; more detial of chunk exp;	3 years ago
Hui Zhang	20117d99ee	fix ckpt load	3 years ago
Hui Zhang	43b52082c3	Merge pull request #629 from PaddlePaddle/align ... ctc alignment	3 years ago
Hui Zhang	4c9a1f6dc7	add align.sh and update run.sh	3 years ago
Hui Zhang	6ee67785f6	fix ctc alignment	3 years ago
Hui Zhang	717fe1e4bd	Merge pull request #680 from PaddlePaddle/checkpoint ... checkpoint refactor to save disk space	3 years ago
Haoxin Ma	c0f7aac8fc	revise conf/*.yaml	3 years ago
Hui Zhang	f8d52e598f	Merge branch 'develop' into rsl	3 years ago
Hui Zhang	03e6952501	more detial of result	3 years ago
Hui Zhang	718bd30765	Merge pull request #688 from PaddlePaddle/ds2_fix ... fix conf for ds2	3 years ago
Hui Zhang	019ae4b35c	fix conf for ds2	3 years ago
Hui Zhang	4b80b172d3	add model params	3 years ago
Hui Zhang	133a522fbb	ds2 default using 4gpu; new result of ds2	3 years ago
Hui Zhang	68149cb9a7	fix config for new datapipeline	3 years ago
Hui Zhang	5a3a9e1f50	fix chunk default config; tarball ckpt prfix dir;	3 years ago
Hui Zhang	8c1bf1a730	fix ds2 conf for new data pipeline	3 years ago
Haoxin Ma	557427736e	move redundant params	3 years ago
Haoxin Ma	698d7a9bdb	move batch_size, work_nums, shuffle_method, sortagrad to collator	3 years ago
Haoxin Ma	6ee3033cc4	finish aishell/s0	3 years ago
Hui Zhang	1cd88d2619	Merge pull request #657 from PaddlePaddle/add_utt ... add utt to datapipeline	3 years ago
Hui Zhang	255a6f004e	result with specaug	3 years ago
Haoxin Ma	8781ab58cf	fix export and run.sh	3 years ago
Hui Zhang	9bb1806246	fix clip conf	3 years ago
Hui Zhang	b3d23e6af3	add stream conf	3 years ago
Hui Zhang	69dfc2a5fa	fix mask for bool type; fix other	3 years ago
Hui Zhang	de780a0c8a	add libri ds2 exp result	4 years ago
Hui Zhang	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
Hui Zhang	1b373bfcd7	refactor g2p egs (#630) ... * refactor g2p egs * add sha-bone; remove avg.sh from egs;	4 years ago
Hui Zhang	0a7958b3f1	add tarball utils (#626)	4 years ago
Hui Zhang	37c5324138	fix result; add feature list	4 years ago
Hui Zhang	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
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	4 years ago
Hui Zhang	d777edc605	ctc decoding weight 0.5 (#614) ... * ctc decoding weight 0.5 * tiny decoding conf * more label of mergify * format doc	4 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	4 years ago
Hui Zhang	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