huangyuxin
|
429221dc03
|
adopt multi machine traiing
|
3 years ago |
huangyuxin
|
ac1b301657
|
Merge branch 'webdataset' of https://github.com/Jackwaterveg/DeepSpeech into webdataset
|
3 years ago |
TianYuan
|
d8a0ba5913
|
Merge pull request #2085 from yt605155624/fix_tts_cli_log
[TTS]fix int32 warning in tts
|
3 years ago |
Jackwaterveg
|
6598216b2f
|
Merge branch 'develop' into webdataset
|
3 years ago |
TianYuan
|
c0f126ecd9
|
fix int32 warning in tts, test=tts
|
3 years ago |
huangyuxin
|
9b5655f6ad
|
fix 'print log' in cli
|
3 years ago |
huangyuxin
|
aa12b9ab52
|
replace s2t.transform with audio.transform
|
3 years ago |
huangyuxin
|
0c7abc1f17
|
add training scripts
|
3 years ago |
TianYuan
|
5ff885f116
|
add tts static/onnx models in pretrained_models.py
|
3 years ago |
huangyuxin
|
c7a7b113c8
|
support multi-gpu training with webdataset
|
3 years ago |
贾晓
|
0fa3fdb9ee
|
Merge pull request #2068 from yt605155624/p_norm
[TTS]add onnx models for aishell3/ljspeech/vctk's tts3/voc1/voc5
|
3 years ago |
TianYuan
|
7743c6a1ff
|
add onnx models for aishell3/ljspeech/vctk's tts3/voc1/voc5, test=tts
|
3 years ago |
KP
|
b230dfbdec
|
Add kws cli and demo.
|
3 years ago |
huangyuxin
|
8f5e61090b
|
new feature: Add webdataset in audio
|
3 years ago |
TianYuan
|
46ff848d66
|
Merge pull request #2056 from lym0302/develop
[server] fix_model_init
|
3 years ago |
Hui Zhang
|
e04cd18846
|
Merge pull request #2050 from zh794390558/onnx_quant
[speechx] ds2 wenetspeech onnx quant
|
3 years ago |
lym0302
|
7d4f320836
|
fix_model_init, test=doc
|
3 years ago |
TianYuan
|
d1aa83a239
|
Merge pull request #2052 from yt605155624/ernie_sat
[TTS]add ernie sat inference
|
3 years ago |
Hui Zhang
|
54a777055a
|
Merge pull request #2039 from iftaken/dev-hym
[demo] speech web demo
|
3 years ago |
Hui Zhang
|
d20adb5c89
|
Merge pull request #2048 from KPatr1ck/import_bug
[CLI][Audio] Fix circular import error in paddlespeech.cli.utils and paddlespeech.audio
|
3 years ago |
TianYuan
|
79658a5f20
|
add ernie sat inference, test=tts
|
3 years ago |
TianYuan
|
02734141ce
|
Merge pull request #2040 from yt605155624/add_blank
[TTS]add blank between characters for vits
|
3 years ago |
Hui Zhang
|
d95b0cd9b2
|
add release and resource
|
3 years ago |
Hui Zhang
|
3cf1f1f0b5
|
support onnx quantize
|
3 years ago |
Jackwaterveg
|
6dfe7273e6
|
Merge pull request #2045 from zh794390558/wenetspeech_onnx
[server] ds2 wenetspeech to onnx and support streaming asr server
|
3 years ago |
KP
|
b452be3d8d
|
Fix circular import error in paddlespeech.cli.utils and paddlespeech.audio
|
3 years ago |
KP
|
220bcffac8
|
Fix circular import error in paddlespeech.cli.utils and paddlespeech.audio
|
3 years ago |
KP
|
fc5f0b14e0
|
Fix circular import error in paddlespeech.cli.utils and paddlespeech.audio
|
3 years ago |
KP
|
fe345409bb
|
Fix circular import error in paddlespeech.cli.utils and paddlespeech.audio
|
3 years ago |
huangyuxin
|
c552c0877f
|
fix ds2 server config
|
3 years ago |
Hui Zhang
|
d21e6d8adb
|
fix window ms config
|
3 years ago |
Hui Zhang
|
59a78f2a46
|
ds2 wenetspeech to onnx and support streaming asr server
|
3 years ago |
huangyuxin
|
704b5f8bc4
|
fix win len in ds2 server
|
3 years ago |
Hui Zhang
|
0f8e9cdd32
|
add init file
|
3 years ago |
iftaken
|
357b177232
|
rename readme and fixed conflict
|
3 years ago |
TianYuan
|
1731976e4e
|
add blank between characters for vits, test=tts
|
3 years ago |
Hui Zhang
|
73d702fd6a
|
Merge branch 'develop' into asr_ol
|
3 years ago |
Hui Zhang
|
27f2833bf7
|
format
|
3 years ago |
iftaken
|
cb50999096
|
Merge branch 'develop' of github.com:PaddlePaddle/PaddleSpeech into dev-hym
|
3 years ago |
Hui Zhang
|
5e03d753ac
|
add ds2 steaming asr onnx
|
3 years ago |
Hui Zhang
|
cd0b82ff1b
|
fix pretrain model error
|
3 years ago |
Hui Zhang
|
9106daa2a3
|
code format
|
3 years ago |
Hui Zhang
|
42d28b961c
|
fix pretrian model error
|
3 years ago |
iftaken
|
474373bceb
|
Merge branch 'develop' into dev-hym
|
3 years ago |
Hui Zhang
|
4851d1d3a2
|
Merge branch 'onnx' into asr_ol
|
3 years ago |
Hui Zhang
|
d66bfefd01
|
update aishell ds2 streaming onnx model
|
3 years ago |
Hui Zhang
|
ff3b1ff817
|
opt onnx script
|
3 years ago |
Hui Zhang
|
3cee7db021
|
onnx ds2 straming asr
|
3 years ago |
Hui Zhang
|
b4c6a52beb
|
Merge pull request #2034 from zh794390558/onnx
[speechx] deepseech2 to onnx
|
3 years ago |
Hui Zhang
|
c8574c7e35
|
ds2 inference as sepearte engine for streaming asr
|
3 years ago |
Hui Zhang
|
b9e3e49305
|
refactor stream asr and fix ds2 stream bug
|
3 years ago |
Jackwaterveg
|
bca014fd92
|
Merge pull request #2032 from PaddlePaddle/audio_refactoring
[audio] Audio refactoring
|
3 years ago |
Hui Zhang
|
1628e19bce
|
Merge branch 'develop' into onnx
|
3 years ago |
KP
|
4aaa8effe8
|
Refactor paddleaudio to paddlespeech.audio
|
3 years ago |
KP
|
bf056c013d
|
Refactor paddleaudio to paddlespeech.audio
|
3 years ago |
liangym
|
e0c0804ce3
|
Merge pull request #2025 from Jackwaterveg/fix
[CLI ]fix cli
|
3 years ago |
huangyuxin
|
2b5bc6df39
|
fix cli, test=doc
|
3 years ago |
Jackwaterveg
|
b4e868ac0f
|
Merge pull request #2020 from Jackwaterveg/develop_dev
[CLI] update ds2 wenetspeech model info,support static model
|
3 years ago |
Hui Zhang
|
28c1794b9b
|
format
|
3 years ago |
huangyuxin
|
678cd15354
|
update model, test=doc
|
3 years ago |
Jackwaterveg
|
05fd9a0e2c
|
Merge pull request #2019 from Jackwaterveg/develop_dev
[Server] update reademe, add conf file, updata test_cli
|
3 years ago |
huangyuxin
|
06c9eee339
|
update reademe, add conf file, updata test_cli
|
3 years ago |
Hui Zhang
|
1f5f34a815
|
Merge pull request #2016 from Jackwaterveg/develop_dev
[ASR] Support editing num_decode_left_chunks in cli and server
|
3 years ago |
Hui Zhang
|
262f42d49f
|
do not reset result for web ws api
|
3 years ago |
huangyuxin
|
6ebe476532
|
support editing num_decode_left_chunks in cli and server
|
3 years ago |
Hui Zhang
|
dfdf450b22
|
fix #2013; and format
|
3 years ago |
Hui Zhang
|
69a6da4c16
|
ctc endpoint work
|
3 years ago |
Hui Zhang
|
8f9b7bba48
|
refactor asr online server
|
3 years ago |
lym0302
|
90b7f88eb5
|
fix hifigan pad value
|
3 years ago |
liangym
|
919c8d0607
|
Merge branch 'PaddlePaddle:develop' into update_engine
|
3 years ago |
Hui Zhang
|
82c1f4c508
|
Merge pull request #1997 from Jackwaterveg/develop_dev
[ASR] refactor ds2, cli, server with espent datapipeline
|
3 years ago |
TianYuan
|
84d13dea18
|
Merge pull request #2002 from KPatr1ck/resource
[Resource] Fix tts_online server issue. test=doc
|
3 years ago |
KP
|
613b689017
|
Fix tts_online server issue. test=doc
|
3 years ago |
liangym
|
8b1c1ec43f
|
Merge branch 'PaddlePaddle:develop' into update_engine
|
3 years ago |
TianYuan
|
1a6df85f97
|
Merge pull request #2000 from yt605155624/fix_chunk
[TTS]reneame chunk to block in streaming tts, test=tts
|
3 years ago |
huangyuxin
|
e48e1d5e81
|
fix tiny and local script, test=asr
|
3 years ago |
KP
|
f77b8ede74
|
Fix server issues.
|
3 years ago |
TianYuan
|
004ab8d0c0
|
reneame chunk to block in streaming tts, test=tts
|
3 years ago |
liangym
|
4a11257dcb
|
Merge branch 'develop' into update_engine
|
3 years ago |
KP
|
46690b1b3c
|
Fix windows issue in paddlespeech.resource
|
3 years ago |
huangyuxin
|
47dd61e5b2
|
refactor ds2, cli, server
|
3 years ago |
Hui Zhang
|
0fa32e4aae
|
Merge pull request #1917 from KPatr1ck/resource
[Resource][CLI][Server] Add paddlespeech.resource module.
|
3 years ago |
KP
|
6436f343bb
|
Fix asr_inference server engine.
|
3 years ago |
TianYuan
|
aa3d151d1d
|
Merge pull request #1994 from Jackwaterveg/develop
[ASR] not install ctc on win
|
3 years ago |
huangyuxin
|
10819e0fa2
|
not install ctc on win, test=asr
|
3 years ago |
lym0302
|
d48c4d686a
|
update engine, test=doc
|
3 years ago |
KP
|
6a08221525
|
Add paddlespeech.resource.
|
3 years ago |
KP
|
1e066fab9e
|
Add paddlespeech.resource.
|
3 years ago |
KP
|
dcea088c66
|
Add paddlespeech.resource.
|
3 years ago |
KP
|
7766d7344d
|
Add paddlespeech.resource.
|
3 years ago |
KP
|
fa6e44e4ff
|
Add paddlespeech.resource.
|
3 years ago |
TianYuan
|
b6ad4260eb
|
fix bug in tts cli, test=tts
|
3 years ago |
Hui Zhang
|
42fba661c9
|
more detail of copyright
|
3 years ago |
Hui Zhang
|
3d88ac4e68
|
Merge pull request #1950 from Jackwaterveg/develop
[ASR] fix pad_sequence, remove paddle.size, paddle.static.Variable.size, using paddle.shape()
|
3 years ago |
TianYuan
|
7bc54cbbe6
|
Merge pull request #1957 from yt605155624/vits_doc
[doc]add VITS readme, test=tts
|
3 years ago |
KP
|
6c57c2bf8e
|
Dynamic cli commands registration.
|
3 years ago |
TianYuan
|
f9f014d159
|
add VITS readme, test=tts
|
3 years ago |
Hui Zhang
|
6f7917b7f2
|
fix streaming asr
|
3 years ago |
Hui Zhang
|
f07f57a3a8
|
Merge pull request #1945 from PaddlePaddle/asr_line
[server][asr] refactor asr streaming server and remove useless code
|
3 years ago |
Hui Zhang
|
8f8239ad3b
|
Merge pull request #1954 from Honei/acs_server
[server][vector]update the vector model
|
3 years ago |
xiongxinlei
|
be8a78a9d1
|
fix the vector model type error, test=doc
|
3 years ago |
xiongxinlei
|
a5605978fa
|
update the acs note, test=doc
|
3 years ago |
xiongxinlei
|
a83374a787
|
update the vector readme, test=doc
|
3 years ago |
xiongxinlei
|
7afbdbefad
|
update the vector model, test=doc
|
3 years ago |
huangyuxin
|
b23bde8ec5
|
tensor.shape => paddle.shape(tensor)
|
3 years ago |
huangyuxin
|
4c09927f61
|
fix
|
3 years ago |
huangyuxin
|
e1888f9ae6
|
remove size,test=asr
|
3 years ago |
Zhangjingyu06
|
acb19cf465
|
deepspeech2 modify for kunlun
|
3 years ago |
Zhangjingyu06
|
b0eaeccd67
|
deepspeech2 modify for kunlun
|
3 years ago |
Zhangjingyu06
|
1e91f7da35
|
deepspeech2 modify for kunlun
|
3 years ago |
huangyuxin
|
1cdd41bd03
|
fix pad_sequence, test=asr
|
3 years ago |
TianYuan
|
5ee3cc0c31
|
Merge pull request #1855 from yt605155624/add_vits
[TTS]add vits network scripts, test=tts
|
3 years ago |
Hui Zhang
|
c15278ed80
|
format
|
3 years ago |
TianYuan
|
327509951f
|
rm unused comment, test=tts
|
3 years ago |
TianYuan
|
433ebf2594
|
Merge pull request #1940 from yt605155624/rm_fluid
[TTS]rm fluid in tts, test=tts
|
3 years ago |
Hui Zhang
|
943272385a
|
refactor asr online
|
3 years ago |
TianYuan
|
c1b512c58a
|
rm fluid in tts, test=tts
|
3 years ago |
huangyuxin
|
ea71fddbde
|
fix condition of wenetspeech
|
3 years ago |
Jackwaterveg
|
3638320f3b
|
fix self.max_len
|
3 years ago |
huangyuxin
|
008c812f63
|
fix cli/asr
|
3 years ago |
TianYuan
|
df3f975ea5
|
Merge branch 'develop' of github.com:PaddlePaddle/PaddleSpeech into add_vits
|
3 years ago |
TianYuan
|
58028509c3
|
replace dynamic_import
|
3 years ago |
iftaken
|
2938d3e49b
|
Merge branch 'develop' into dev-hym
|
3 years ago |
TianYuan
|
8db06444c5
|
add vits trainer and synthesize
|
3 years ago |
Honei
|
bde7093578
|
Merge pull request #1906 from Honei/acs_server
[acs][server]add audio content search server
|
3 years ago |
Hui Zhang
|
4b3f6c615e
|
Merge pull request #1913 from Honei/timelimit
[asr][server]add asr time limt configuration
|
3 years ago |
xiongxinlei
|
b1ef434983
|
update the max len compute method, test=doc
|
3 years ago |
xiongxinlei
|
0ea39f837b
|
add asr time limt configuration, test=doc
|
3 years ago |
xiongxinlei
|
25ee960571
|
refair the acs note, test=doc
|
3 years ago |
TianYuan
|
e61757dbf7
|
fix yao, test=tts
|
3 years ago |
xiongxinlei
|
3535079434
|
update the acs engine doc, test=doc
|
3 years ago |
xiongxinlei
|
d94ab22e92
|
acs server, test=doc
|
3 years ago |
xiongxinlei
|
f57fff24fb
|
update the init flag, test=doc
|
3 years ago |
xiongxinlei
|
67939d0d66
|
add check asr server model type, test=doc
|
3 years ago |
lym0302
|
c5d2224d6d
|
fix cors, test=doc
|
3 years ago |
iftaken
|
c7dd207038
|
fixs CORS Error
|
3 years ago |
Hui Zhang
|
a11dc53c1b
|
Merge pull request #1888 from Jackwaterveg/develop
[Server] fix server doc and decode_method
|
3 years ago |
root
|
88501fc32a
|
fix server doc and decode_method
|
3 years ago |
Jerryuhoo
|
167aaa65b9
|
normalize wav max value to 1 in preprocess, test=tts
|
3 years ago |
liangym
|
22b67ed051
|
Merge pull request #1882 from lym0302/streaming_tts_server
[server] improve code
|
3 years ago |
Hui Zhang
|
f86317893e
|
Merge pull request #1884 from Honei/develop
[server]change vector train.py local_rank to rank
|
3 years ago |
lym0302
|
be21aed09b
|
trans remove file way, test=doc
|
3 years ago |
lym0302
|
b1f9b8016d
|
add start and end request on ws tts, test=doc
|
3 years ago |
xiongxinlei
|
347af638e2
|
changet vector train.py local_rank to rank, test=doc
|
3 years ago |
lym0302
|
d4f863dc97
|
improve, test=doc
|
3 years ago |
pollyyan
|
018dda6ee9
|
Merge pull request #1879 from QingshuChen/develop
speedyspeech support kunlun
|
3 years ago |
Hui Zhang
|
c23a97e242
|
Merge pull request #1877 from Jackwaterveg/develop
[ASR] Replace dist.spawn with dist.launch
|
3 years ago |
Hui Zhang
|
5b053cde6a
|
Merge pull request #1878 from Honei/develop
[server]update the vector and text readme
|
3 years ago |
xiongxinlei
|
06bea5f03d
|
update the vector and text readme, test=doc
|
3 years ago |
QingshuChen
|
e55177c3db
|
speedyspeech support kunlun
|
3 years ago |
root
|
9f389a7a33
|
support cpu, test=asr
|
3 years ago |
root
|
864041085f
|
replace dist.spawn with dist.launch, test=asr
|
3 years ago |
TianYuan
|
4b7786f2ed
|
add vits network scripts, test=tts
|
3 years ago |
KP
|
19d015b60a
|
Add RFT for asr task.
|
3 years ago |
KP
|
da08f1c1af
|
Add RFT for asr task.
|
3 years ago |
Hui Zhang
|
12ae137c83
|
update tts_api for ws
|
3 years ago |
Hui Zhang
|
175c67b75e
|
asr socket to asr api
|
3 years ago |
Hui Zhang
|
7be6b0e8cf
|
unify name style & frame with abs timestamp
|
3 years ago |
Hui Zhang
|
15b25199c2
|
Merge pull request #1864 from zh794390558/doc
[doc] update readme with new feature
|
3 years ago |
xiongxinlei
|
bb0db29d7e
|
update the streaming asr readme, test=doc
|
3 years ago |
root
|
4d7046d244
|
updata released model info, test=doc
|
3 years ago |
liangym
|
e7a35485e4
|
Merge pull request #1859 from lym0302/update_readme
[server] improve server code
|
3 years ago |
Hui Zhang
|
02e7586394
|
update readme
|
3 years ago |
lym0302
|
b361a73888
|
improve server code, test=doc
|
3 years ago |
Hui Zhang
|
94aaa61726
|
Merge pull request #1858 from KPatr1ck/cli_version
[CLI]Add version command in cli.
|
3 years ago |
KP
|
677898ab96
|
Add version command in cli.
|
3 years ago |
Hui Zhang
|
13503613b4
|
Merge pull request #1853 from Jackwaterveg/develop
[CLI] update cli
|
3 years ago |
root
|
3a7896fc96
|
update cli, test=asr
|
3 years ago |
liangym
|
e87495f045
|
[server] update readme (#1851)
* update readme, test=doc
* update readme, test=doc
* update readme, test=doc
|
3 years ago |
Hui Zhang
|
37c6106ee0
|
Merge pull request #1848 from zh794390558/spx
[speechx] rm to_float32 flags, default feature fbank
|
3 years ago |
Hui Zhang
|
8522b82999
|
format
|
3 years ago |
xiongxinlei
|
b7a77eebca
|
update the time stamp type, test=doc
|
3 years ago |
Honei
|
43582f5091
|
Merge branch 'develop' into asr_time
|
3 years ago |
Hui Zhang
|
d99e99ce2c
|
Merge pull request #1836 from Honei/punc
[asr][server]join streaming asr and punc server
|
3 years ago |
Hui Zhang
|
435e86b335
|
Merge pull request #1835 from Honei/vec_server
[vec][server]add vector server
|
3 years ago |
xiongxinlei
|
10da21a77b
|
update the vector cli for server, test=doc
|
3 years ago |
xiongxinlei
|
2ab96187aa
|
streaming asr server add time stamp, test=doc
|
3 years ago |
xiongxinlei
|
c78653850b
|
join streaming asr and punc server, test=doc
|
3 years ago |
xiongxinlei
|
3950557e04
|
update the vector server note, test=doc
|
3 years ago |
xiongxinlei
|
b1dddddbe0
|
add vector server, test=doc
|
3 years ago |
Jerryuhoo
|
fba0693a20
|
fix random speaker embedding bug, test=tts
|
3 years ago |
Hui Zhang
|
cdb9a1b20b
|
Merge pull request #1813 from Honei/v0.3
[R1.0]update the paddlespeech_client asr_online cli
|
3 years ago |
Honei
|
ff7dbcc2de
|
Merge branch 'develop' into v0.3
|
3 years ago |
xiongxinlei
|
f7af037cb1
|
add the note for offline asr, test=doc
|
3 years ago |
xiongxinlei
|
3f80464926
|
update the streaming asr readme, test=doc
|
3 years ago |
Hui Zhang
|
fc96130fdc
|
fix speechx core dump when stop immediately after start
|
3 years ago |
xiongxinlei
|
c5fe181405
|
update the paddlespeech_client asr_online cli, test=doc
|
3 years ago |
huangyuxin
|
4494f5a1fc
|
add cli models, test=doc
|
3 years ago |
Hui Zhang
|
903cc67a4d
|
Merge pull request #1801 from Honei/v0.3
[R1.0]update the streaming output and punc default ip, port
|
3 years ago |
xiongxinlei
|
e844e0e0bb
|
update the streaming output and punc default ip, port, test=doc
|
3 years ago |
huangyuxin
|
18197cd3a5
|
renew ds2 model, test=doc
|
3 years ago |
Hui Zhang
|
ebde26030b
|
patch func to var
|
3 years ago |
Honei
|
f72cbc9b6d
|
Merge branch 'develop' into v0.3
|
3 years ago |
xiongxinlei
|
9125cb076d
|
update the ws asr response, final_result to result, test=doc
|
3 years ago |
xiongxinlei
|
7007b0ecac
|
update the asr server api, test=doc
|
3 years ago |
Hui Zhang
|
5e23025c31
|
fix speechx ws server to return dummpy partial result, fix hang for ws client
|
3 years ago |
Hui Zhang
|
d7c8c1779f
|
Merge pull request #1786 from Jackwaterveg/debug
[CLI] renew ds2 online model
|
3 years ago |
Hui Zhang
|
9cc7662512
|
Merge pull request #1782 from lym0302/add_streaming_cli
[server] update readme
|
3 years ago |
huangyuxin
|
e145b26355
|
fix
|
3 years ago |
huangyuxin
|
4f9e8bfa90
|
renew ds2 online, test=doc
|
3 years ago |