260752aa2a
using forward_attention_decoder
2 years ago
8690a00bd8
add feature pipeline layer(cmvn, fbank), but to_static and jit.layer output is not equal
2 years ago
3a8869fba4
rm to_static decarator; configure jit save for ctc_activation
2 years ago
1c9f238ba0
configurable export
2 years ago
63aeb747b0
more comment
2 years ago
d638325c46
do not jit save forward; using slice for zeros([0,0,0,0]) tensor
2 years ago
2bb40c41ba
Merge pull request #2351 from Zth9730/fix_deepspeech
...
[s2t] fix deepspeech2 decode_wav
2 years ago
ab92e2c98c
fix deepspeech2 decode_wav
2 years ago
795eb7bd10
format paddlespeech with pre-commit ( #2331 )
2 years ago
c1fbfe928e
add test
2 years ago
6149daa221
export ctc_activation
2 years ago
e5a6c243f1
fix jit save for conformer
2 years ago
4e7106d9e2
Support dy2st
2 years ago
05d41523ad
Merge branch 'develop' into webdataset
2 years ago
92d1d08b9a
fix scripts
2 years ago
98cfdc4c05
fix nxpu
2 years ago
7463df89c5
fix nxpu
2 years ago
aa12b9ab52
replace s2t.transform with audio.transform
2 years ago
c7a7b113c8
support multi-gpu training with webdataset
2 years ago
dfdf450b22
fix #2013 ; and format
2 years ago
e48e1d5e81
fix tiny and local script, test=asr
2 years ago
47dd61e5b2
refactor ds2, cli, server
2 years ago
acb19cf465
deepspeech2 modify for kunlun
2 years ago
b0eaeccd67
deepspeech2 modify for kunlun
2 years ago
1e91f7da35
deepspeech2 modify for kunlun
2 years ago
9f389a7a33
support cpu, test=asr
2 years ago
864041085f
replace dist.spawn with dist.launch, test=asr
2 years ago
8d1ee8262e
Merge branch 'develop' into CER
2 years ago
6e80618e3d
add ds2
2 years ago
efc269b75f
remove unuseful code, test=doc
2 years ago
89b102a7dd
fix the ws send bug, cache buffer, text=doc
2 years ago
e1b581b622
fix some bug, test=asr
2 years ago
d53e1163a6
update the code, test=asr
2 years ago
aefe9e93a7
add tipc benchmark of conformer
2 years ago
d7222c0453
[ASR] Support CTC decoder online ( #821 )
...
* fix the destructer problem for prefixes
* unified offline and online in ctcdecoders, test=asr
* rename swig_decoders to paddlespeech_ctcdecoders, test=asr
* add reset_stage for ctcdecoder
* fix some problems
* fix ctconline
* fix a bug
* fix the format
* fix 1xt2x
2 years ago
44408e5211
sync the variable name to others
3 years ago
43aad7a018
beam search with optimality guarantees
3 years ago
5e7e8a3e24
fix the u2 export, test=asr
3 years ago
e69abc9265
Merge pull request #1273 from zh794390558/batch_sampler
...
[s2t] Fix Batch sampler set epoch
3 years ago
07d457859d
use pre-commit, test=doc_fix
3 years ago
45832f6770
fix default dist_samlper to False
3 years ago
3a2db414e6
format code
3 years ago
6f651d762e
fix batch sampler set_epoch when epcoh start
3 years ago
8b63485ce3
fix some bug, test=asr
3 years ago
3e2cc898cb
remove default cfg and fix some bugs,test=asr
3 years ago
a1d8ab0f99
merge the develop
3 years ago
c907a8deda
change all recipes
3 years ago
c81a3f0f83
[s2t] DataLoader with BatchSampler or DistributeBatchSampler ( #1242 )
...
* batchsampler or distributebatchsampler
* format
3 years ago
420709e5ce
[st] Distributed sampler and new dataloader with MIMO ( #1239 )
...
* update timit result, test=doc_fix
* result update
* fix bug
* add triplet loader
* empty preprocess file
* sync to u2, updating
* sync to u2 config
* fix bugs
* code refine
* update config
* customize decoding batch size
* update optimizer and lr scheduler
* minor
* minor
* minor
* fix bugs of refs
* minor
* distributed sampler
* minor
* refine the loader
3 years ago
41eeed0450
add librispeech asr1
3 years ago
2c5902d7c5
rename decoding to decode
3 years ago
bb2a370b23
[asr] remove useless conf of librispeech ( #1227 )
...
* remve useless conf
* format code
* update conf
* update conf
* update conf
3 years ago
c40b6f4062
refactor the train and test config,test=asr
3 years ago
db121226b8
clean aishell asr1 conf & compare ctc loss with torch and warpctc_pytorch ( #1191 )
3 years ago
68164dd39f
[asr]rename test_hub to test_wav ( #1132 )
...
* add the readme, librispeech_asr1
* fix the test_hub
* test=asr
3 years ago
5b446f6321
[Config]clear the u2 decode config for asr ( #1107 )
...
* clear the u2 decode config
* rename the vocab_filepath and cmvn_path
3 years ago
2189b46004
add tts cli
3 years ago
0818c1601d
add __init__.py
3 years ago
4e31a4445d
eval mode
3 years ago
39228864bb
format code
3 years ago
7554b6107a
using visualdl; fix read_manifest
3 years ago
cdd0845127
add translate function
3 years ago
895a086fdd
rename the config.feat_size and the config.vocab.size to input_size and output_size
3 years ago
fe83adfbcb
nproc to ngpu
3 years ago
789471bfca
test wav for u2
3 years ago
8aebfeac81
fix the prc-commit
3 years ago
2ba3f00bbd
Merge branch 'develop' into datapipe
3 years ago
fb6974f950
update the auto_log
3 years ago
1ae1ead80f
more install scripts
3 years ago
51a6845564
Merge pull request #985 from Jackwaterveg/benchmark
...
revise the benchmark
3 years ago
843ea1c12e
revise the benchmark
3 years ago
080b0431f4
format code
3 years ago
7c8843448c
add word reward into beam search.
3 years ago
7ceef6c3f5
format code
3 years ago
f9221b4b74
fix ctc align
3 years ago
fb853167d3
format code
3 years ago
9cdd2643b1
fix bug for batch dataloader using
3 years ago
69bccb4f02
fix ctc align
3 years ago
69055698a2
transformer using batch data loader
3 years ago
d647cde870
change the lm dataset dir
3 years ago
e2bcaee4f1
merge deepspeech, parakeet and text_processing into paddlespeech
3 years ago
Hui Zhang
tianhao zhang
TianYuan
0x45f
huangyuxin
Zhangjingyu06
root
Jackwaterveg
xiongxinlei
Junkun