zxcd
|
c0cf9e9d3d
|
adapt paddle 3.2, remove some hack code to avoid conflict. (#4120)
|
2 weeks ago |
|
zxcd
|
8247eba840
|
add paramters name (#4119)
|
2 weeks ago |
co63oc
|
f2b4b947a7
|
Fix typos in multiple files (#4032)
|
6 months ago |
|
zxcd
|
0479cce8ff
|
【audio】remove paddleaudio from paddlespeech (#3986)
* remove paddleaudio from paddlespeech
* use scikit-learn instead sklearn
* add pathos
* remove utils
* add kaldiio
* remove useless print
|
7 months ago |
张春乔
|
25741d7038
|
【Hackathon 8th No.7】Python版本适配 1 (#3965)
* fix setup.py
* Update generator.py
* fix optional
* Update setup.py
|
8 months ago |
megemini
|
553a9db374
|
[Fix] emb init (#3962)
|
9 months ago |
|
megemini
|
b4c2f3bae3
|
[Hackathon 7th] 修复 `s2t` 示例错误 (#3950)
* [Fix] s2t
* [Fix] s2t test
|
9 months ago |
Wang Xin
|
62c21e951f
|
replace view with reshape in aishell/asr1 (#3887)
|
10 months ago |
luyao-cv
|
f2416ff365
|
fix develop bug function:view to reshape (#3633)
|
2 years ago |
Hui Zhang
|
d94db47f78
|
fix rotary embeding
|
2 years ago |
|
Hui Zhang
|
0a5cc5556e
|
rope for streaming decoding
|
2 years ago |
|
Hui Zhang
|
b56fb85ca0
|
RoPE with position interpolation
|
2 years ago |
|
Hui Zhang
|
b91b1c9b08
|
support position interpolation for langer attention context windown length.
|
2 years ago |
|
Hui Zhang
|
55870ffbb3
|
fix bugs
|
2 years ago |
|
Hui Zhang
|
03e9ea9e52
|
add roformer
|
2 years ago |
夜雨飘零
|
31a4562ae8
|
[ASR]add squeezeformer model (#2755)
* add squeezeformer model
* change CodeStyle, test=asr
* change CodeStyle, test=asr
* fix subsample rate error, test=asr
* merge classes as required, test=asr
* change CodeStyle, test=asr
* fix missing code, test=asr
* split code to new file, test=asr
* remove rel_shift, test=asr
|
3 years ago |
YangZhou
|
42ff946007
|
[audio] mv paddlespeech/audio to paddleaudio (#2706)
* split paddlespeech/audio to paddleaudio.
* add sox io ,sox effect, kaldi native fbank to paddleaudio.
|
3 years ago |
tianhao zhang
|
1ea828c30e
|
fix attention val bug
|
3 years ago |
|
tianhao zhang
|
3d994f5c23
|
format wav2vec2 demo
|
3 years ago |
|
Hui Zhang
|
9277fcb8a8
|
fix attn can not train
|
3 years ago |
|
Hui Zhang
|
925abcca23
|
format
|
3 years ago |
|
Hui Zhang
|
feb27e2a84
|
fuse linear kv
|
3 years ago |
|
Hui Zhang
|
3adb20b468
|
eliminate shape and slice
|
3 years ago |
|
Hui Zhang
|
46088c0a16
|
elimiate attn transpose
|
3 years ago |
|
Hui Zhang
|
f9e3eaa024
|
transpose in matmul
|
3 years ago |
|
Hui Zhang
|
3d7ca93861
|
bool type slice
|
3 years ago |
|
Hui Zhang
|
c2c8a662b1
|
refactor reshape
|
3 years ago |
|
Hui Zhang
|
6de81d74d9
|
elimiete cast dtype for bool op
|
3 years ago |
|
Hui Zhang
|
b7388ce25a
|
eliminate useless unsqueese
|
3 years ago |
|
Hui Zhang
|
00b2c1c8fb
|
fix forward attention decoder caller
|
3 years ago |
|
Hui Zhang
|
9b66680ea4
|
Merge branch 'u2++_decoder' into u2pp_export
|
3 years ago |
|
tianhao zhang
|
0a95689461
|
support bitransformer decoder
|
3 years ago |
|
tianhao zhang
|
1a56a6e42b
|
add bitransformer decoder, test=asr
|
3 years ago |
|
Hui Zhang
|
53d6baff0b
|
format
|
3 years ago |
|
Hui Zhang
|
e3298c79ce
|
Merge branch 'develop' into u2_export
|
3 years ago |
|
Hui Zhang
|
8690a00bd8
|
add feature pipeline layer(cmvn, fbank), but to_static and jit.layer output is not equal
|
3 years ago |
|
Hui Zhang
|
63aeb747b0
|
more comment
|
3 years ago |
|
Hui Zhang
|
d638325c46
|
do not jit save forward; using slice for zeros([0,0,0,0]) tensor
|
3 years ago |
|
tianhao zhang
|
6745e9dd6b
|
fix dp init
|
3 years ago |
TianYuan
|
795eb7bd10
|
format paddlespeech with pre-commit (#2331)
|
3 years ago |
|
tianhao zhang
|
cdcb1a5316
|
s2t: fix encoder.py
|
3 years ago |
|
tianhao zhang
|
ed2819d7af
|
fix format test=asr
|
3 years ago |
|
tianhao zhang
|
ed80b0e2c3
|
fix multigpu training test=asr
|
3 years ago |
|
tianhao zhang
|
733ec7f2bc
|
fix conformer multi-gpu training test=asr
|
3 years ago |
|
Hui Zhang
|
ef37f73a01
|
fix cnn cache dy2st shape
|
3 years ago |
0x45f
|
e6ac8881f1
|
Fix comments
|
3 years ago |
|
0x45f
|
ac680aa783
|
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into new_api
|
3 years ago |
|
0x45f
|
294b7b00bd
|
Supprot dy2st for conformer
|
3 years ago |
huangyuxin
|
75997d8277
|
merge
|
3 years ago |
|
Hui Zhang
|
e81849277e
|
att cache for streaming asr
|
3 years ago |
