b079577e08
merge parakeet repo into deepspeech
3 years ago
b453b425af
add readthedoc
3 years ago
366e34c925
update paddle version to 2.1.2
3 years ago
f15e1ff732
fix doc link
3 years ago
bad7f91857
fix readme
3 years ago
c9578cf940
remove useless link
3 years ago
f54dc983b6
using bw rnn in ds2
3 years ago
c81743403a
fix
3 years ago
c09b0e8940
fix specaug
3 years ago
4c0ee8d354
fix conf and readme
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
2ff726a66e
fix doc link ( #627 )
4 years ago
37c5324138
fix result; add feature list
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
538bf271eb
chinese char/word ngram lm ( #613 )
...
* add ngram lm egs
* add zhon repo
* install kenlm, zhon
* format
* add chinese_text_normalization repo
* add ngram lm egs
4 years ago
db022fac6e
fix doc ( #611 )
4 years ago
90512c3964
Fix readme install link ( #610 )
4 years ago
c6ae9857f2
update doc ( #603 )
...
* fix doc format
* 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
9ac99f7cc6
disscusion for questions, issue only for bug report ( #573 )
4 years ago
d4e84f9b9d
fix doc link and enhance install ( #570 )
...
* fix doc link
* fix install
* fix install doc
* fix typo
* fix lm doc
4 years ago
aaafe1417d
Update README.md
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
a43ee0ff86
update en readme
4 years ago
141109b49d
update aishell egs
4 years ago
c246d315b5
update en readme
4 years ago
f965d72f3f
update readme
4 years ago
126677a35c
support py3
4 years ago
01019fb92b
update grad_clip to 1.8
5 years ago
a70a70a51d
update README.md and README_cn.md
5 years ago
a78922d5e1
Merge pull request #393 from AshishKarel/patch-1
...
Update Readme
5 years ago
1b4117efdd
Update Readme
...
Python command to normalize the data have some typo errors.
5 years ago
31e7a95141
Update README.md added missing yum install package
...
Update README.md added missing yum install package `python-devel` which is required by python package `resampy`.
5 years ago
d5ee83b074
update README
5 years ago
827a8c8ea3
update README
5 years ago
261844b3da
update README
5 years ago
7da06fb5ee
upadte README.md and README_cn.md
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
b8a6d3b969
Update README.md
5 years ago
13ec49de95
Update README.md
5 years ago
f19a58c2bf
Update README.md
5 years ago
445d84ee26
Update lm & acoustic models' link
6 years ago
9aef6d2b6b
Fix the issues link in README
7 years ago
9c5daab08d
Update benchmark result for BaiduEN8K model due to #88
7 years ago
0823cd2ce4
Upload BaiduCN1.2k model.
7 years ago
6c2d0e61b5
fix the link to cloud training in doc
7 years ago
ccb4332fe3
update benchmark result for English model
7 years ago
cd5f558bc7
Add library boost to the dependency
7 years ago
61177a10b2
update the rebuilt docker repo's name in doc
7 years ago
f862e0c646
Merge branch 'develop' of upstream into fix_docker_doc
7 years ago
74e00f4e15
add more info in the setup section
7 years ago
5ba0e0a00b
update setup in readme
7 years ago
a200271ba9
Update libri model.
7 years ago
45760ebf16
Merge pull request #16 from pkuyym/fix-9
...
Add script for VoxForge data preparation.
7 years ago
adc117312f
Refine doc and fix path for run_data.sh
7 years ago
b5f70d5fcf
Refine doc.
7 years ago
abbfa43b22
Add script for VoxForge data preparation.
7 years ago
35ef4624b0
Update url for Aishell model.
7 years ago
0923f3a520
fix doc for Docker
7 years ago
cc5e420331
fix typo
7 years ago
1e3875160c
Add url for BaiduEng8k model.
7 years ago
a0d1146be7
Update benchmark results for LibriSpeech model due to #427
7 years ago
fcd6149704
Update benchmark results for BaiduEN8K model due to #427
7 years ago
f8da5127fe
Update benchmark results for LibriSpeech model
7 years ago
9c897b7256
Merge pull request #421 from xinghai-sun/benchmark
...
Update DS2 benchmark results.
7 years ago
42ef8b3be3
Rename: Eng --> EN, Chi --> CN
7 years ago
84155d1548
Update DS2 benchmark results.
7 years ago
a6bffa59ec
Merge pull request #364 from pkuyym/fix-361
...
Add document for Mandarin model.
7 years ago
046f6ca994
Refine doc.
7 years ago
963b60d5ed
Refine doc for Mandarin training.
7 years ago
31d8e7e033
Merge pull request #418 from kuke/docker_doc_dev
...
Add the document about docker running for DS2
7 years ago
6f90a33f1f
Update the doc about docker running for DS2
7 years ago
3e048a3c9a
Add the doc about docker running for DS2
7 years ago
1f6a18e8e8
Refine doc.
7 years ago
e8a5a17b1d
Refine doc.
7 years ago
d78d4fa6ff
Add url for large Mandarin LM.
7 years ago
9b7fc7e903
Add doc for Chinese LM.
7 years ago
e3bb689c0e
Add document for Mandarin model.
7 years ago
e909396f91
Refine doc.
7 years ago
0057ca1fb5
Add doc for mandarin lm.
7 years ago
a87e3d0f61
Refine doc.
7 years ago
35543fff8b
Add doc for english LM.
7 years ago
c66a40d7ac
Merge branch 'develop' of upstream into add_tuning_fig
7 years ago
cc3570d406
format some writings
7 years ago
285972e36e
Update experimental results for DS2.
7 years ago
27d6cf90d1
add figure for tuning & enrich the tuning section in doc
7 years ago
e8dce3a982
Add README doc section of multi-gpu acceleration.
7 years ago
3bb746c61f
Add last two sections (experiments and model released) to README.md.
7 years ago
351f61e366
Update RAEDME.md and librispeech.py by following Yaming's review.
7 years ago
ac56a2f249
Update READMD.md and other details by following reviewers comments.
7 years ago
35caf5e0b7
Add bash code highlight to README.md for DS2.
7 years ago
4969d297d8
Correct typos for DS2 README.md.
7 years ago
87453365b2
Update REAME.md for DS2.
7 years ago
e11b735de5
Update examples scripts and REAME.md for DS2.
7 years ago
a00a436b52
Rewrite README.md doc (50%) and correct some bugs.
7 years ago
861b946d7a
Re-design README.md doc structure and add table of contents.
7 years ago
5623b09868
Move decoder.py to models and re-arrange unitests.
7 years ago
0bbb9c3ee2
Re-organize folder structure and hierarchy for DS2.
7 years ago
5e13fd7dad
deep speech2 can directly use warpctc instead by export LD_LIBRARY_PATH
7 years ago
da28015556
Update README for DS2 cloud training.
7 years ago
9e08727c95
remove prerequisites part in the readme of DS2
7 years ago
b57dc63e1f
update readme in DS2
7 years ago
1325cd9b8e
Create 'tools' to hold tool scripts and add vocabulary dictionary building script.
7 years ago
7e39debcb0
Convert README.md's file mode to 644.
7 years ago
f4375ef125
Update README.md with code reviews for DS2.
7 years ago
c0b3281e58
Remove pynput and pyaudio packages from requriements.txt and add installation tips to README.md.
8 years ago
b57d244363
Add ASR demo usage to README.md for DS2.
8 years ago
a48469b9b6
add the requirement for cuDNN version in README
8 years ago
c7676286ab
install libsndfile from /usr to thirdparty
8 years ago
cb0680e8c4
follow comments to modify README.md
8 years ago
724ef18596
update several scripts to support mfcc
8 years ago
ee5abbe37d
add mfcc feature for DS2
8 years ago
8ce9546710
modify README.md
8 years ago
d15c48d616
upload the language model
8 years ago
aeccd9851b
append README.md
8 years ago
13f708739b
Improve audio featurizer and add shift augmentor.
...
1. Improve audio featurizer.
2. Add shift augmentor.
3. Update default argument to be the current best seggestion.
4. Add checkpoints with pass id.
8 years ago
a5dcd23bf2
Follow comments.
8 years ago
1cef98f210
Update README.md for DS2.
8 years ago
06e9f71389
Remove manifest's line number check from librispeech.py and update README.md.
8 years ago
d3eeb7fd76
Refine librispeech.py for DeepSpeech2.
...
Summary:
1. Add manifest line check.
2. Avoid re-unpacking if unpacked data already exists.
3. Add full_download (download all 7 sub-datasets of LibriSpeech).
8 years ago
730d5c4dd3
Update DS2 README.md and fix bug in librispeech.py
8 years ago
2a83486500
Refactor decoder interfaces and add ./data directory.
8 years ago
8313895e85
1. Fix incorrect decoder result printing.
...
2. Fix incorrect batch-norm usage in RNN.
3. Fix overlapping train/dev/test manfests.
4. Update README.md and requirements.txt.
5. Expose more arguments to users in argparser.
6. Update all other details.
8 years ago
70a343a499
Add infererence and add SortaGrad for only first pass.
8 years ago
3fc94427db
Add librispeech dataset, audio data provider and simplfied DeepSpeech2 model configuration.
...
Bug exists when run training.
8 years ago
d59b8ca97e
Add deep_speech_2 folder.
8 years ago
Hui Zhang
huangyuxin
Zeyu Chen
lfchener
AshishKarel
Harisankar H
Yibing Liu
Xinghai Sun
yangyaming
Hu Weiwei
Xinghai Sun
Luo Tao