megemini
|
2d7cf7f0e6
|
[Hackathon 7th] 修复 `asr4` 的 `test_wav` 多余的 argument (#3940)
* [Fix] test_wav parse arg
* [Fix] remove line
|
2 weeks ago |
张春乔
|
5069111e6d
|
[Hackathon 7th] 修复 deepspeech2online 的导出问题 (#3935)
* Update model.py
* Update model.py
|
2 weeks ago |
|
megemini
|
e3c4d4bd7e
|
[Fix] use reshape instead of view (#3939)
|
2 weeks ago |
|
megemini
|
d17361cf8c
|
[Fix] duplicated arg (#3934)
|
3 weeks ago |
|
megemini
|
ff539ef007
|
[Fix] transpose use numpy (#3933)
|
3 weeks ago |
|
megemini
|
890c87ea93
|
[Fix] import TimeDomainSpecAugment (#3919)
|
4 weeks ago |
yinfan98
|
5b3612f273
|
【Hackathon 7th】fix whisper at Paddle 3.0 (#3880)
* fix whisper at Paddle 3.0
* fix whisper at Paddle 3.0
* fix whisper at Paddle 3.0
* fix lint
* fix
* fix whisper ci
* Update TTSCppFrontend
* Update utils
* Update steps
* Update utils
* Update __init__.py
* Update whisper.py
* Update utils
* Update utils
|
4 weeks ago |
|
megemini
|
5e8c727fd6
|
[Hackathon 7th] 修复 `tal_cs` 测试中 0D tensor to 1D (#3913)
* [Fix] 0D tensor to 1D
* [Update] feat dim
|
4 weeks ago |
|
megemini
|
a397ebe207
|
[Fix] import print_arguments (#3918)
|
4 weeks ago |
Wang Xin
|
61728f8db6
|
NumPy compatibility enhancements (#3907)
* NumPy compatibility enhancements
* update code
|
1 month ago |
|
张春乔
|
7dc806dc1d
|
run with aishell/asr3 (#3904)
|
1 month ago |
zxcd
|
d32ced7f1a
|
separate paddle.logsumexp (#3897)
|
1 month ago |
|
zxcd
|
89bfd44293
|
fix file name (#3895)
|
1 month ago |
|
Wang Xin
|
62c21e951f
|
replace view with reshape in aishell/asr1 (#3887)
|
1 month ago |
|
张春乔
|
6f44ac92c8
|
fix the shape error in layer_norm (#3884)
|
1 month ago |
|
张春乔
|
419af4503c
|
【Hackathon 7th】Remove parser.add_argument (#3878)
* Update test_wav.py
* Update export.py
* Update test_export.py
* Update model.py
* Update README.md
* Apply suggestions from code review
* Apply suggestions from code review
* Update README.md
* Update README.md
* Update test.py
* Update README.md
|
1 month ago |
|
张春乔
|
290d161d8a
|
【Hackathon 7th】add implemention of strtobool (#3877)
* add implemention of strtobool
* Apply suggestions from code review
* Apply suggestions from code review
* Apply suggestions from code review
|
1 month ago |
|
zxcd
|
91170bd260
|
adapt view behavior change, fix KeyError. (#3794)
* adapt view behavior change, fix KeyError.
* fix readme demo run error.
* fixed opencc version
|
7 months ago |
jzhang533
|
969f33999f
|
Merge pull request #3538 from fazledyn-or/develop
Fixed implementation of a special method
|
10 months ago |
luyao-cv
|
f2416ff365
|
fix develop bug function:view to reshape (#3633)
|
1 year ago |
fazledyn-or
|
1a693448fa
|
FIX: Fixed the implementation of a special method
|
1 year ago |
|
fazledyn-or
|
1113a68a6d
|
FIX: Added missing imports
|
1 year ago |
Wang Huan
|
790f183f68
|
fix develop view confict with model's
|
1 year ago |
Hui Zhang
|
2faa49a39f
|
fix weight decay
|
1 year ago |
|
Hui Zhang
|
d94db47f78
|
fix rotary embeding
|
1 year ago |
|
Hui Zhang
|
0a5cc5556e
|
rope for streaming decoding
|
1 year ago |
|
Hui Zhang
|
b56fb85ca0
|
RoPE with position interpolation
|
1 year ago |
|
Hui Zhang
|
b91b1c9b08
|
support position interpolation for langer attention context windown length.
|
1 year ago |
|
Hui Zhang
|
55870ffbb3
|
fix bugs
|
1 year ago |
|
Hui Zhang
|
03e9ea9e52
|
add roformer
|
1 year ago |
|
zxcd
|
5fee985dd1
|
remove fluid.
|
2 years ago |
|
Hui Zhang
|
a2ae6396ef
|
old grad clip has 0d tensor problem, fix it (#3334)
|
2 years ago |
|
zxcd
|
9b8ac050de
|
add dtype param for arange API. (#3302)
|
2 years ago |
jiamingkong
|
8432e8626f
|
Final cleaning; Modified SSL/infer.py and README for wavlm inclusion in model options
|
2 years ago |
|
jiamingkong
|
ba874db5dc
|
Fixed the transpose usages ignored before
|
2 years ago |
|
jiamingkong
|
0e2068e2cf
|
Code clean up for CIs
|
2 years ago |
|
jiamingkong
|
232dcf8660
|
Adapted wavlmASR model to pretrained weights and CLI
|
2 years ago |
|
jiamingkong
|
60bd7f202e
|
Code clean up according to comments in https://github.com/PaddlePaddle/PaddleSpeech/pull/3242
|
2 years ago |
|
jiamingkong
|
3b6651ba7c
|
Adding WavLM implementation
|
2 years ago |
TianHao Zhang
|
12e3e76092
|
[ASR] Support Hubert, fintuned on the librispeech dataset (#3088)
* librispeech hubert, test=asr
* librispeech hubert, test=asr
* hubert decode
* review
* copyright, notes, example related
* hubert cli
* pre-commit format
* fix conflicts
* fix conflicts
* doc related
* doc and train config
* librispeech.py
* support hubert cli
|
2 years ago |
|
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 |
Shuangchi He
|
8c7859d3bc
|
Fix some typos. (#3178)
Signed-off-by: Yulv-git <yulvchi@qq.com>
|
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
|
2f4414a5f8
|
fix scaler save
|
2 years ago |
|
zxcd
|
fbd27aab41
|
add amp for U2 conformer.
|
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
|
2 years ago |
