Hui Zhang
|
8371d14f5d
|
Merge pull request #3167 from zxcd/amp
[ASR] add amp for U2 conformer
|
2 years ago |
Hui Zhang
|
225737d4e3
|
[s2t] fix cli args to config (#3194)
* fix cli args to config
* fix train cli
|
2 years ago |
zxcd
|
bc365cbb52
|
Merge branch 'develop' into amp
|
2 years ago |
Hui Zhang
|
df3be4acae
|
[s2t] move s2t data preprocess into paddlespeech.dataset (#3189)
* move s2t data preprocess into paddlespeech.dataset
* avg model, compute wer, format rsl into paddlespeech.dataset
* fix format rsl
* fix avg ckpts
|
2 years ago |
zxcd
|
a1e5f27003
|
mv scaler.unscale_ blow grad_clip.
|
2 years ago |
zxcd
|
7399d560e7
|
fix scaler save and load.
|
2 years ago |
zxcd
|
fbd27aab41
|
add amp for U2 conformer.
|
2 years ago |
Hui Zhang
|
2c34481ea0
|
[s2t] quant with wav scp (#2568)
* add quant hint
* add paddleslim
* using paddleslim 2.3.4 and paddle 2.4
|
2 years ago |
YangZhou
|
bbf2401e3e
|
Merge pull request #2524 from zh794390558/u2
[speechx] add u2/u2pp asr inference
|
2 years ago |
Hui Zhang
|
290c23b9d7
|
add u2 nnet, u2 nnet main, codelab, and can compile
|
2 years ago |
tianhao zhang
|
cda440e6f0
|
use reverse_weight in decode.yaml
|
2 years ago |
Hui Zhang
|
1f4f98b171
|
fix bug
|
2 years ago |
Hui Zhang
|
e86337a423
|
fix bug
|
2 years ago |
Hui Zhang
|
2a75405e9a
|
Merge branch 'develop' into u2pp_export
|
2 years ago |
Hui Zhang
|
3ed24474d2
|
wenetspeech asr1 quant
|
2 years ago |
tianhao zhang
|
5bbe6e9897
|
support u2pp cli and server, optimiz code of u2pp decode, test=asr
|
2 years ago |
Hui Zhang
|
8e7a315e00
|
remove comment
|
2 years ago |
Hui Zhang
|
00b2c1c8fb
|
fix forward attention decoder caller
|
2 years ago |
Hui Zhang
|
309c8d70d9
|
add reverse weight
|
2 years ago |
Hui Zhang
|
9b66680ea4
|
Merge branch 'u2++_decoder' into u2pp_export
|
2 years ago |
tianhao zhang
|
027535dec1
|
support bitransformer decoder, test=asr
|
2 years ago |
tianhao zhang
|
0a95689461
|
support bitransformer decoder
|
2 years ago |
tianhao zhang
|
455379b88e
|
support bitransformer decoder
|
2 years ago |
tianhao zhang
|
1a56a6e42b
|
add bitransformer decoder, test=asr
|
2 years ago |
Hui Zhang
|
53d6baff0b
|
format
|
2 years ago |
Hui Zhang
|
549d477592
|
fix code style
|
2 years ago |
Hui Zhang
|
4d5cfd4003
|
export param from cnofig
|
2 years ago |
Hui Zhang
|
260752aa2a
|
using forward_attention_decoder
|
2 years ago |
Hui Zhang
|
8690a00bd8
|
add feature pipeline layer(cmvn, fbank), but to_static and jit.layer output is not equal
|
2 years ago |
Hui Zhang
|
3a8869fba4
|
rm to_static decarator; configure jit save for ctc_activation
|
2 years ago |
Hui Zhang
|
1c9f238ba0
|
configurable export
|
2 years ago |
Hui Zhang
|
63aeb747b0
|
more comment
|
2 years ago |
Hui Zhang
|
d638325c46
|
do not jit save forward; using slice for zeros([0,0,0,0]) tensor
|
2 years ago |
TianYuan
|
795eb7bd10
|
format paddlespeech with pre-commit (#2331)
|
2 years ago |
Hui Zhang
|
c1fbfe928e
|
add test
|
2 years ago |
Hui Zhang
|
6149daa221
|
export ctc_activation
|
2 years ago |
Hui Zhang
|
e5a6c243f1
|
fix jit save for conformer
|
2 years ago |
0x45f
|
4e7106d9e2
|
Support dy2st
|
2 years ago |
huangyuxin
|
92d1d08b9a
|
fix scripts
|
2 years ago |
huangyuxin
|
aa12b9ab52
|
replace s2t.transform with audio.transform
|
2 years ago |
huangyuxin
|
c7a7b113c8
|
support multi-gpu training with webdataset
|
2 years ago |
root
|
9f389a7a33
|
support cpu, test=asr
|
3 years ago |
root
|
864041085f
|
replace dist.spawn with dist.launch, test=asr
|
3 years ago |
xiongxinlei
|
efc269b75f
|
remove unuseful code, test=doc
|
3 years ago |
xiongxinlei
|
89b102a7dd
|
fix the ws send bug, cache buffer, text=doc
|
3 years ago |
huangyuxin
|
e1b581b622
|
fix some bug, test=asr
|
3 years ago |
huangyuxin
|
d53e1163a6
|
update the code, test=asr
|
3 years ago |
huangyuxin
|
aefe9e93a7
|
add tipc benchmark of conformer
|
3 years ago |
huangyuxin
|
5e7e8a3e24
|
fix the u2 export, test=asr
|
3 years ago |
Jackwaterveg
|
e69abc9265
|
Merge pull request #1273 from zh794390558/batch_sampler
[s2t] Fix Batch sampler set epoch
|
3 years ago |