Hui Zhang
|
e9da7e0e07
|
[runtime] add logging module, build on linux and android, normalize option name (#2986)
* rename option with WITH_; add logging module to replace with glog
* refactor logging module; build pass on linux and andorid
|
1 year ago |
|
Hui Zhang
|
b35fc01a3a
|
opt to compile asr,cls,vad; add vad; format code (#2968)
|
1 year ago |
masimeng1994
|
78e29c8ec4
|
add cls engine (#2923)
|
1 year ago |
TianYuan
|
2f8aad95e0
|
Update .mergify.yml
|
1 year ago |
YangZhou
|
8e1b4cd513
|
[engine] rename speechx (#2892)
* rename speechx
* fix wfst decode error
* replace reset with make_unique
|
1 year ago |
|
YangZhou
|
21183d48b6
|
add wfst decoder (#2886)
|
1 year ago |
|
YangZhou
|
5042a1686a
|
[speechx] add batch recognizer decode. (#2866)
* add recognizer_batch
|
1 year ago |
|
YangZhou
|
8a225b1708
|
[speechx] thread decode (#2839)
* fix nnet thread crash && rescore cost time
* add nnet thread main
|
2 years ago |
|
YangZhou
|
ee7c266f13
|
[speechx] rm openblas && refactor kaldi-matrix, kaldi-vector (#2824)
* rm openblas && refactor kaldi-matrix kaldi-vector
|
2 years ago |
|
YangZhou
|
c1b1ae0515
|
[speechx]add kaldi-native-fbank && refactor frontend (#2794)
* replace kaldi-fbank with kaldi-native-fbank
* make kaldi-native-fbank work
|
2 years ago |
|
YangZhou
|
acf1d27230
|
[speechx] rm ds2 && rm boost (#2786)
* fix openfst download error
* add acknowledgments of openfst
* refactor directory
* clean ctc_decoders dir
* add nnet cache && make 2 thread work
* do not compile websocket
* rm ds2 && rm boost
* rm ds2 example
|
2 years ago |
|
YangZhou
|
5046d8ee94
|
[Speechx] add nnet prob cache && make 2 thread decode work (#2769)
* add nnet cache && make 2 thread work
* do not compile websocket
|
2 years ago |
|
Hui Zhang
|
f8caaf46c8
|
refactor cmake, rm absl/linsndfile, add strings unittest (#2765)
|
2 years ago |
|
YangZhou
|
869f4267d5
|
[speechx]Speechx directory refactor (#2746)
* refactor directory
|
2 years ago |
|
YangZhou
|
7804c8e8f3
|
[speechx]fix openfst download error (#2742)
* fix openfst download error
* add acknowledgments of openfst
|
2 years ago |
|
Hui Zhang
|
aa91adc60e
|
update u2++ ctc prefix beam search result (#2736)
|
2 years ago |
zxcd
|
a8a240d4ef
|
remove paddle.fluid (#2740)
|
2 years ago |
|
YangZhou
|
12fa8a2d19
|
[audio]patch:fix tensor_utils error (#2738)
* fix tensor utils
|
2 years ago |
|
YangZhou
|
4afa28701c
|
update paddle from 2.4.0rc to 2.4.1 in readme (#2732)
* update paddle from 2.4.0rc to 2.4.1 in readme
|
2 years ago |
|
YangZhou
|
d35dda0020
|
add scikit-learn in setup.py (#2733)
|
2 years ago |
|
TianYuan
|
e1a43ddb4e
|
Update release_note.py
|
2 years ago |
|
TianYuan
|
3f6afc4834
|
[TTS]Add slim for TTS (#2729)
|
2 years ago |
|
Hui Zhang
|
6f927d55db
|
onnx ds2 need onnxruntime>=1.11.0 (#2728)
|
2 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.
|
2 years ago |
|
Hui Zhang
|
0cc54bb785
|
fix speechx cmake for find python3 (#2723)
|
2 years ago |
|
Hui Zhang
|
2e9ac304ed
|
add paddle commit that u2++ quant model cer 5.8% (#2714)
|
2 years ago |
|
TianYuan
|
a3d5d93dd4
|
Update README_cn.md
|
2 years ago |
|
TianYuan
|
56447a32f1
|
Update README.md
|
2 years ago |
|
TianYuan
|
e29bf59aaf
|
Update README_cn.md
|
2 years ago |
|
TianYuan
|
f5f17ab3f9
|
Update README.md
|
2 years ago |
|
TianYuan
|
001b22cf41
|
Update README.md
|
2 years ago |
|
TianYuan
|
f5380af32e
|
Update requirements.txt
|
2 years ago |
HuangLiangJie
|
a874d8f325
|
Add prosody prediction in synthesize_e2e, test=tts (#2693)
|
2 years ago |
|
Hui Zhang
|
b4ea7bfc0a
|
[speechx] fix bugs (#2710)
|
2 years ago |
|
TianYuan
|
62357d876c
|
[TTS]rm paddlelite in setup.py (#2713)
* rm paddlelite in setup.py
* fix setup.py
|
2 years ago |
Zth9730
|
062a00c21c
|
[doc] update released_model.md, test=doc (#2705)
* update released_model.md, test=doc
* Update released_model.md
|
2 years ago |
|
zxcd
|
4275c73afb
|
update whisper model source (#2704)
|
2 years ago |
|
Hui Zhang
|
03ad2a0f98
|
[speechx] update speechx docker usage (#2707)
|
2 years ago |
|
TianYuan
|
d0b35077b7
|
Update README_cn.md
|
2 years ago |
|
TianYuan
|
54f672a960
|
Update README.md
|
2 years ago |
|
TianYuan
|
e0a5c0f7de
|
[TTS]add TTSAndroid demo (#2703)
* add TTSAndroid demo
|
2 years ago |
|
Hui Zhang
|
d71d1273ed
|
[speechx] more doc for speechx (#2702)
* doc for ds2 websocket
|
2 years ago |
|
zxcd
|
1ffe3561ae
|
add paddlenlp install version. (#2701)
|
2 years ago |
|
Zth9730
|
c67bf7b4ef
|
[ASR] support wav2vec2-zh cli, test=asr (#2697)
* support wav2vec2-zh cli, test=asr
* support wav2vec2-zh cli, test=asr
* support wav2vec2-zh cli, test=asr
* support wav2vec2-zh cli, test=asr
|
2 years ago |
|
Hui Zhang
|
a01c163dc3
|
[speechx] more doc of speechx u2 and ds2 onnx (#2692)
* more doc of speechx u2 onnx
|
2 years ago |
David An （An Hongliang）
|
bd01bc155d
|
add greek char and fix issue2571 (#2683)
Co-authored-by: TianYuan <white-sky@qq.com>
|
2 years ago |
heyudage
|
58309aa9d7
|
update docs test=doc (#2688)
|
2 years ago |
|
zxcd
|
4542684694
|
[ASR] fix Whisper cli model download path error. test=asr (#2679)
* add all whisper model size support
* add choices in parser.
* fix Whisper cli model download path error.
* fix resource download path.
* fix code style
|
2 years ago |
|
Zth9730
|
fc02cd0540
|
[doc] update wav2vec2 demos README.md, test=doc (#2674)
* fix wav2vec2 demos, test=doc
* fix wav2vec2 demos, test=doc
* fix enc_dropout and nor.py, test=asr
|
2 years ago |
|
zxcd
|
b71f1428c7
|
add all whisper model size support, test=asr (#2677)
* add all whisper model size support
* add choices in parser.
|
2 years ago |
