94a487bd81
[ASR] support wav2vec2 command line and demo ( #2658 )
...
* wav2vec2_cli
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* Update RESULTS.md
* Update RESULTS.md
* Update base_commands.py
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
2 years ago
b1d3f59bcb
[s2t] add whisper asr large model ( #2640 )
...
* add whisper asr large model decoding, test=asr
* fix code style.
* fix json code style.
* remove resource and fix code style.
* fix yapf
* add cli and demos, fix some code style.
* fix some problem by comment.
* fix yapf
2 years ago
8d3494320d
[ASR] wav2vec2_en, test=asr ( #2637 )
...
* wav2vec2_en, test=asr
* wav2vec2_en, test=asr
* wav2vec2_en, test=asr
2 years ago
2c34481ea0
[s2t] quant with wav scp ( #2568 )
...
* add quant hint
* add paddleslim
* using paddleslim 2.3.4 and paddle 2.4
2 years ago
8d3464c050
[s2t] Update wav2vec2 license ( #2600 )
2 years ago
bbf2401e3e
Merge pull request #2524 from zh794390558/u2
...
[speechx] add u2/u2pp asr inference
2 years ago
eac545e1db
Merge pull request #2544 from Zth9730/fix_attention
...
[s2t] fix attention eval bug, do not compose kv in infer
2 years ago
1ea828c30e
fix attention val bug
2 years ago
964c22c677
Merge pull request #2532 from Zth9730/wav2vec2.0
...
[s2t] fix wav2vec2 report loss bug
2 years ago
86f65f0b8e
fix wav2vec2 report loss bug
2 years ago
f1ca564731
Merge pull request #2518 from Zth9730/wav2vec2.0
...
[ASR] wav2vec2 ASR, pre-trained wav2vec2 based CTC for librispeech
2 years ago
2ae94bd277
freeze wav2vec2=True, change loss report and update README.md
2 years ago
3d994f5c23
format wav2vec2 demo
2 years ago
19180d359d
format wav2vec2 demo
2 years ago
6e429f0513
support wav2vec2ASR on librispeech
2 years ago
290c23b9d7
add u2 nnet, u2 nnet main, codelab, and can compile
2 years ago
cda440e6f0
use reverse_weight in decode.yaml
2 years ago
c98b5dd173
fix masked_fill which will nan in trainning
2 years ago
9277fcb8a8
fix attn can not train
2 years ago
1f4f98b171
fix bug
2 years ago
e86337a423
fix bug
2 years ago
925abcca23
format
2 years ago
2a75405e9a
Merge branch 'develop' into u2pp_export
2 years ago
3ed24474d2
wenetspeech asr1 quant
2 years ago
467cfd4e75
Merge pull request #2489 from Zth9730/u2++_server
...
[ASR] support u2pp based cli and server, optimiz code of u2pp decode (reversed_weight parameter)
2 years ago
5bbe6e9897
support u2pp cli and server, optimiz code of u2pp decode, test=asr
2 years ago
bdf876ea7b
Merge branch 'develop' into u2pp_export
2 years ago
afda7ed7d1
remove useless code
2 years ago
b20bf7d5de
masked_fill by multiply, remove while
2 years ago
feb27e2a84
fuse linear kv
2 years ago
3adb20b468
eliminate shape and slice
2 years ago
46088c0a16
elimiate attn transpose
2 years ago
f9e3eaa024
transpose in matmul
2 years ago
3d7ca93861
bool type slice
2 years ago
c2c8a662b1
refactor reshape
2 years ago
6de81d74d9
elimiete cast dtype for bool op
2 years ago
8e7a315e00
remove comment
2 years ago
b7388ce25a
eliminate useless unsqueese
2 years ago
1a1ce92cb4
Merge pull request #2415 from Zth9730/u2++_decoder
...
[s2t] support bitransformer decoder
2 years ago
d3e5937591
support bitransformer decoder
2 years ago
7382050e21
fix bug on win
2 years ago
d25871a7b0
format
2 years ago
b10512eb0e
more config or u2pp
2 years ago
00b2c1c8fb
fix forward attention decoder caller
2 years ago
309c8d70d9
add reverse weight
2 years ago
9b66680ea4
Merge branch 'u2++_decoder' into u2pp_export
2 years ago
027535dec1
support bitransformer decoder, test=asr
2 years ago
0a95689461
support bitransformer decoder
2 years ago
455379b88e
support bitransformer decoder
2 years ago
1a56a6e42b
add bitransformer decoder, test=asr
2 years ago
53d6baff0b
format
2 years ago
549d477592
fix code style
2 years ago
4d5cfd4003
export param from cnofig
2 years ago
e3298c79ce
Merge branch 'develop' into u2_export
2 years ago
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
663e3ab58e
fix dp init
2 years ago
6745e9dd6b
fix dp init
2 years ago
598eb1a5ef
Merge branch 'develop' into fix_dp_init
2 years ago
9560d650db
fix dp init
2 years ago
82e04d7815
fix trianer
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
cdcb1a5316
s2t: fix encoder.py
2 years ago
ed2819d7af
fix format test=asr
2 years ago
ed80b0e2c3
fix multigpu training test=asr
2 years ago
733ec7f2bc
fix conformer multi-gpu training test=asr
2 years ago
c1fbfe928e
add test
2 years ago
05bc258833
update docstring
2 years ago
6149daa221
export ctc_activation
2 years ago
060e337623
fix dataloader factory, test=asr
2 years ago
812d80ab1c
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into u2_export
2 years ago
e5a6c243f1
fix jit save for conformer
2 years ago
4e7106d9e2
Support dy2st
2 years ago
ef37f73a01
fix cnn cache dy2st shape
2 years ago
e21cceea51
Remove blank line
2 years ago
e6ac8881f1
Fix comments
2 years ago
ac680aa783
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into new_api
2 years ago
294b7b00bd
Supprot dy2st for conformer
2 years ago
75997d8277
merge
2 years ago
e81849277e
att cache for streaming asr
2 years ago
fb40602d94
refactor attention cache
2 years ago
05d41523ad
Merge branch 'develop' into webdataset
2 years ago
92d1d08b9a
fix scripts
2 years ago
e4a8e15334
Merge pull request #2111 from yt605155624/rm_more_log
...
[CLI]replace logger.info with logger.debug in cli, change default log leve…
2 years ago
496e2dd14b
fix Pillow's version
2 years ago
bc93bffbb4
replace logger.info with logger.debug in cli, change default log level to INFO
2 years ago
98cfdc4c05
fix nxpu
2 years ago
7463df89c5
fix nxpu
2 years ago
6ec6921255
Merge branch 'webdataset' of https://github.com/Jackwaterveg/DeepSpeech into webdataset
2 years ago
6598216b2f
Merge branch 'develop' into webdataset
2 years ago
9b5655f6ad
fix 'print log' in cli
2 years ago
aa12b9ab52
replace s2t.transform with audio.transform
2 years ago
0c7abc1f17
add training scripts
2 years ago
c7a7b113c8
support multi-gpu training with webdataset
2 years ago
Zth9730
zxcd
Hui Zhang
YangZhou
tianhao zhang
TianYuan
huangyuxin
0x45f
Jackwaterveg