5e8dc5c17f
update the deepspech_online.conf
...
set lr_decay from 0.9 to 0.91
3 years ago
08b68e4b8f
change the deepspeech2_online.yaml
3 years ago
61fe292c47
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into ds2_online
3 years ago
718ae52e3f
add from_config function to ds2_oneline and ds2
3 years ago
4c0ee8d354
fix conf and readme
3 years ago
7a3d164122
fix the bidirect rnn, add deepspeech2.yaml for aishell, tiny, librispeech
3 years ago
895330bad3
refactor ted en zh script; fix MAIN_ROOT path
3 years ago
61d8540451
reconstruct the export function and the run.sh in aishell and librispeech
3 years ago
156e324bbb
注释了sever.sh的17-21行
3 years ago
6c4e1361be
fix chunk mode test script
3 years ago
a486f6e618
Merge pull request #730 from PaddlePaddle/doc
...
refactor egs readme
3 years ago
a546b96f85
refactor egs readme
3 years ago
3e5f587537
fix path.sh
3 years ago
40dcbbde26
add srilm install
3 years ago
104743cccc
TLG build pass
3 years ago
f5369abdbe
add TLG utils
3 years ago
8c9e142492
fix kenlm install; librispeech s0 aug
3 years ago
007746bf7f
fix sha bone; more detial of chunk exp;
3 years ago
20117d99ee
fix ckpt load
3 years ago
43b52082c3
Merge pull request #629 from PaddlePaddle/align
...
ctc alignment
3 years ago
4c9a1f6dc7
add align.sh and update run.sh
3 years ago
6ee67785f6
fix ctc alignment
3 years ago
717fe1e4bd
Merge pull request #680 from PaddlePaddle/checkpoint
...
checkpoint refactor to save disk space
3 years ago
c0f7aac8fc
revise conf/*.yaml
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
1cd88d2619
Merge pull request #657 from PaddlePaddle/add_utt
...
add utt to datapipeline
3 years ago
255a6f004e
result with specaug
3 years ago
8781ab58cf
fix export and run.sh
4 years ago
9bb1806246
fix clip conf
4 years ago
b3d23e6af3
add stream conf
4 years ago
69dfc2a5fa
fix mask for bool type; fix other
4 years ago
de780a0c8a
add libri ds2 exp result
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
1b373bfcd7
refactor g2p egs ( #630 )
...
* refactor g2p egs
* add sha-bone; remove avg.sh from egs;
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
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
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
24cb1866a8
Adapt settings for Aishell example.
7 years ago
edaed68f33
Involve dev dataset to build vocabulary in the aishell example
7 years ago
86811af7a3
Reset default value of batch_size, nun_proc_data and fix an invalid url for DS2.
7 years ago
be1fbc68a1
Set process daemon property and reset default value of num_proc_data arguments.
7 years ago
3663ba57d0
make *.sh files more robust in DS2
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
Jackwaterveg
huangyuxin
Hui Zhang
Haoxin Ma
lfchener
yangyaming
Yibing Liu
Xinghai Sun