236 Commits (868d9d933c9653952dda86efa094e0598a3b4619)

Author	SHA1	Message	Date
huangyuxin	7a3d164122	fix the bidirect rnn, add deepspeech2.yaml for aishell, tiny, librispeech	3 years ago
Hui Zhang	1cd4d4bf83	fix tiny conf and refactor optimizer and scheduler	3 years ago
Hui Zhang	4d174b5e2f	fix egs bugs	3 years ago
Hui Zhang	cc813b18d3	fix install and format code	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
Hui Zhang	20d6f9ae4b	Merge pull request #745 from PaddlePaddle/s2 ... kaldi style data for u2 model	3 years ago
Hui Zhang	3864e11302	update librispeech chunk conformer result	3 years ago
Hui Zhang	dc44f552a1	update readme	3 years ago
Hui Zhang	2fd43efb3b	librispeech s2 for kaldi feat	3 years ago
Hui Zhang	74f987aa8f	setup.sh with tools/ make	3 years ago
Hui Zhang	ccdfd5b342	format	3 years ago
Hui Zhang	571b13c53f	add dur utils	3 years ago
Hui Zhang	7278cf9bbb	default chun with all	3 years ago
Hui Zhang	1f2b4ab293	zh 8k egs	3 years ago
Hui Zhang	6c4e1361be	fix chunk mode test script	3 years ago
Hui Zhang	a546b96f85	refactor egs readme	3 years ago
Hui Zhang	73058c196a	libri s0 w/ spec-aug result	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	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	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	9b3acddd5d	fix conf for new datapipe; u2 export inputspec	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	019ae4b35c	fix conf for ds2	3 years ago
Hui Zhang	1cd88d2619	Merge pull request #657 from PaddlePaddle/add_utt ... add utt to datapipeline	3 years ago
Haoxin Ma	8781ab58cf	fix export and run.sh	4 years ago
Hui Zhang	b3d23e6af3	add stream conf	4 years ago
Haoxin Ma	c8368410e2	utt datapipeline	4 years ago
Hui Zhang	34689bd1df	add crf	4 years ago
Hui Zhang	de780a0c8a	add libri ds2 exp result	4 years ago
Hui Zhang	759b2e0b2d	fix ds2 default config	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
Hui Zhang	258307df9b	fix egs bugs (#552) ... * fix egs * fix log	4 years ago
Hui Zhang	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
Hui Zhang	19e0f2ac46	Fix doc format (#546)	4 years ago
Hui Zhang	57ed5cd2e0	Fix Doc (#544)	4 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	141109b49d	update aishell egs	4 years ago
Hui Zhang	7357e52188	fix egs	4 years ago
Hui Zhang	9cfca9fc40	fix dataset dir	4 years ago
Hui Zhang	123d7a6f3f	refactor egs	4 years ago
Hui Zhang	ba7cf0782e	add copyright	4 years ago
Hui Zhang	75c8018eab	refactor tiny egs	4 years ago
Hui Zhang	126677a35c	support py3	4 years ago
lfchener	d89c3a48a7	unify api to 1.6 version and fix some problems	5 years ago
lfchener	d74f4ff3f5	update deepspeech to fluid api	5 years ago
Yibing Liu	3ecf1ad4f5	Decouple ext scorer init & inference & decoding for the convenience of tuning	7 years ago
Yibing Liu	6e4f246517	retune hyper-parameters for librispeech model	7 years ago
Yibing Liu	9800d14956	fix the data path in the librispeech example	7 years ago
Yibing Liu	ad08dd963a	supply param cutoff_top_n in several scripts of DS2	7 years ago
Xinghai Sun	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
Xinghai Sun	86811af7a3	Reset default value of batch_size, nun_proc_data and fix an invalid url for DS2.	7 years ago
yangyaming	758e9887ca	Bug fix for librispeech/run_train.sh.	7 years ago
Xinghai Sun	be1fbc68a1	Set process daemon property and reset default value of num_proc_data arguments.	7 years ago
Yibing Liu	8dcf1d5667	fix bugs in preparing data scripts	7 years ago
Yibing Liu	3663ba57d0	make *.sh files more robust in DS2	7 years ago
Yibing Liu	e6e7b13222	remove the log praser in tuning script	7 years ago
Yibing Liu	4c64841c16	add tuning script & enable ploting error surface	7 years ago
yangyaming	e9a42044f5	Add data preparing for Aishell.	7 years ago
Yibing Liu	3615b44ffd	Merge branch 'develop' of upstream into ctc_decoder_deploy	7 years ago
Xinghai Sun	7f45752a13	Add profile.sh script for multi-gpu profiling.	7 years ago
Yibing Liu	acf2072ed4	Merge branch 'develop' of upstream into ctc_decoder_deploy	7 years ago
yangyaming	1b206b3390	fix bugs for model.py and demo_server.py.	7 years ago
Yibing Liu	7e093ed1a3	expose param cutoff_top_n	7 years ago
Yibing Liu	a18e6a7eda	refine by following review comments	7 years ago
Xinghai Sun	cd635cf6f3	Release librispeech model url.	7 years ago
Yibing Liu	f2120bb5dc	adapt to the new structure	7 years ago
Xinghai Sun	ac56a2f249	Update READMD.md and other details by following reviewers comments.	7 years ago
Xinghai Sun	e11b735de5	Update examples scripts and REAME.md for DS2.	7 years ago
Xinghai Sun	ae7ef7929a	Rename some folders and update examples.	7 years ago
Xinghai Sun	a00a436b52	Rewrite README.md doc (50%) and correct some bugs.	7 years ago
Yibing Liu	8ec4a96523	resolve conflicts in model.py	7 years ago
Yibing Liu	7d0458c7f7	adapt to the new folder structure of DS2	7 years ago
Luo Tao	69e0d86ddb	fix wrong path in prepare.sh	7 years ago
Xinghai Sun	0bbb9c3ee2	Re-organize folder structure and hierarchy for DS2.	7 years ago