887a101eee
update cli unit test, test=doc
3 years ago
940390a443
[CLI] Add unit test ( #1321 )
...
* add test_cli.sh
* set -e
3 years ago
d5f05edc2e
fix some bug, test=asr
3 years ago
c907a8deda
change all recipes
3 years ago
b1c80c45e0
remove ctc grad norm type in config
3 years ago
385881b3f3
update_bs
3 years ago
cb383a39c3
fix the benchmark
3 years ago
2bbfdbae91
Merge pull request #1015 from yt605155624/fs2_conformer
...
[TTS]fastspeech2 conformer
3 years ago
469329221b
refactor encoder, rm old code
3 years ago
fe83adfbcb
nproc to ngpu
3 years ago
2d808a3c64
fix urls
3 years ago
3d5e078c91
add conformer
3 years ago
3ecb8cbfdd
update benchmark case
3 years ago
97878ff43d
update benchmark case
3 years ago
a6d4d67333
update benchmark case
3 years ago
bd0a8aeeaa
update benchmark case
3 years ago
fb47744a2d
update benchmark case
3 years ago
843ea1c12e
revise the benchmark
3 years ago
499666a791
update pwgan benchmark case
3 years ago
bacdf5756b
Merge remote-tracking branch 'origin/develop' into merge_paddlespeech
3 years ago
35c37ace17
change nprocs to ngpu, add aishell3/voc1
3 years ago
d35daff501
fix pwgan benchmark
3 years ago
d8e4b31405
fix asr unit test
3 years ago
e2bcaee4f1
merge deepspeech, parakeet and text_processing into paddlespeech
3 years ago
20226b4fdd
fix benchmark and chain, add parse_options in run.sh, move tacotron2_ge2e into voice_cloning
3 years ago
bfda49bf40
fix the bug of benchmark after merge the parakeet, add the condition of using kaldi in aishll s1
3 years ago
b079577e08
merge parakeet repo into deepspeech
3 years ago
55654ee335
fix the bug of doc in benchmark
3 years ago
566bd02ed2
update the benchmark
3 years ago
4a4998852f
Merge pull request #881 from LittleChenCc/develop
...
update timit result
3 years ago
ad6d09d622
Merge pull request #879 from PaddlePaddle/debug
...
fix ctc loss not convergence
3 years ago
cc7de50267
revise the run_benchmark.sh
3 years ago
25c0f23b17
update the installing script for openfst
3 years ago
c8e96d732b
bool logical, sum and multiply op; ctc grad norm; support old and new pd api
3 years ago
af3d2bd51e
update chain test
3 years ago
913b2300c3
nprocs 0 for cpu, other for gpu
3 years ago
b9beea5ab1
fix bench
3 years ago
cda6ca8323
add benchmark flags, and logic
3 years ago
0f3e5a3872
run_all with aishell/s1
3 years ago
16b9c33deb
format
3 years ago
438e1bd34f
add benmark scripts
3 years ago
797ca389fc
paddle support some bool op
3 years ago
9ac6d65a2a
Merge pull request #780 from Jackwaterveg/ds2_online
...
修改pre_commit, 注释以及增加ds2的seed
3 years ago
9068c0d4f9
Merge branch 'HEAD_1' into ds2_online
3 years ago
718407b77d
add seed
3 years ago
8b67763dab
Merge branch 'fix_auto_log' of https://github.com/Jackwaterveg/DeepSpeech into full_chain
3 years ago
e5add7aab3
add the test.sh
3 years ago
520658050f
add the test.sh
3 years ago
718ae52e3f
add from_config function to ds2_oneline and ds2
3 years ago
722c55e4c5
reconstruct the rnn state, from list to tensor
3 years ago
3fb9f6885a
complete model export for ds2_online
3 years ago
e8a3913422
merge develop_ds2_online
3 years ago
2f64ae6495
not change decoder
3 years ago
4b5cbe9a12
ds2_online alignment, include prob_chunk_forward, prob_chunk_by_chunk_forward
3 years ago
d398270f95
æå增加了chunk_by_chunk,初步测试å通过ã
3 years ago
e4ef8ed31e
add the subsampling as conv
3 years ago
6baf9f0620
跑通了deeppseech_online的流程
3 years ago
4f392e28b1
complete the encoder of ds_online
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
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
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
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
b2eb008a71
Remove test_setup.py.
7 years ago
5623b09868
Move decoder.py to models and re-arrange unitests.
7 years ago
dfd7652308
Rename ctc_best_path_decoder to ctc_greedy_decoder in unitest.
7 years ago
04970705d6
Add more test cases and make DP more clear.
7 years ago
14d2fb795c
Unify encoding to 'utf-8' and optimize error rate calculation.
7 years ago
de212572ed
update unittest with comments
7 years ago
b72b70e54c
add soundfile read/write unitest
7 years ago
7d7984b8fb
add test for libsndfile installation
7 years ago
37e98df74d
enable resetting params in scorer
7 years ago
8ba98cb518
fix decoders' unittest
8 years ago
26510f74a6
refine ctc_beam_search_decoder
8 years ago
8033845615
add unit test for decoders
8 years ago
def66a3223
Follow comments.
8 years ago
26eb54eb37
Follow comments.
8 years ago
f85f8558cf
Add unittest.
8 years ago
TianYuan
Jackwaterveg
huangyuxin
Hui Zhang
hysunflower
mmglove
Xinghai Sun
yangyaming
Luo Tao
Yibing Liu
yangyaming