tianhao zhang
|
1ea828c30e
|
fix attention val bug
|
2 years ago |
Hui Zhang
|
9277fcb8a8
|
fix attn can not train
|
2 years ago |
|
Hui Zhang
|
925abcca23
|
format
|
2 years ago |
|
Hui Zhang
|
feb27e2a84
|
fuse linear kv
|
2 years ago |
|
Hui Zhang
|
46088c0a16
|
elimiate attn transpose
|
2 years ago |
|
Hui Zhang
|
f9e3eaa024
|
transpose in matmul
|
2 years ago |
|
tianhao zhang
|
6745e9dd6b
|
fix dp init
|
2 years ago |
|
tianhao zhang
|
ed80b0e2c3
|
fix multigpu training test=asr
|
2 years ago |
|
tianhao zhang
|
733ec7f2bc
|
fix conformer multi-gpu training test=asr
|
2 years ago |
huangyuxin
|
75997d8277
|
merge
|
2 years ago |
|
Hui Zhang
|
e81849277e
|
att cache for streaming asr
|
2 years ago |
|
Hui Zhang
|
fb40602d94
|
refactor attention cache
|
2 years ago |
|
huangyuxin
|
d53e1163a6
|
update the code, test=asr
|
3 years ago |
|
huangyuxin
|
ab16d8ce3c
|
change default initializer to kaiming_uniform, test=asr
|
3 years ago |
|
Hui Zhang
|
3bd87bc379
|
add wenet lincense
|
3 years ago |
|
Hui Zhang
|
38cf56295a
|
fix reference format
|
3 years ago |
|
Hui Zhang
|
c463a00f81
|
add reference code license
|
3 years ago |
|
Hui Zhang
|
e2bcaee4f1
|
merge deepspeech, parakeet and text_processing into paddlespeech
|
3 years ago |
