Zth9730
|
c9b0c96b7b
|
Merge pull request #2502 from zh794390558/u2pp_export
[s2t] streaming conformer u2 and u2pp jit export
|
2 years ago |
Hui Zhang
|
c98b5dd173
|
fix masked_fill which will nan in trainning
|
2 years ago |
|
Hui Zhang
|
9277fcb8a8
|
fix attn can not train
|
2 years ago |
|
Hui Zhang
|
1f4f98b171
|
fix bug
|
2 years ago |
liangym
|
0359c3f6b5
|
Fix mix front (#2493)
* update mix frontend, test=tts
|
2 years ago |
|
Hui Zhang
|
e86337a423
|
fix bug
|
2 years ago |
|
Hui Zhang
|
925abcca23
|
format
|
2 years ago |
|
Hui Zhang
|
2a75405e9a
|
Merge branch 'develop' into u2pp_export
|
2 years ago |
|
Hui Zhang
|
3ed24474d2
|
wenetspeech asr1 quant
|
2 years ago |
|
Hui Zhang
|
467cfd4e75
|
Merge pull request #2489 from Zth9730/u2++_server
[ASR] support u2pp based cli and server, optimiz code of u2pp decode (reversed_weight parameter)
|
2 years ago |
tianhao zhang
|
5b5167b586
|
support u2pp cli and server, optimiz code of u2pp decode, test=asr
|
2 years ago |
YangZhou
|
3507829a6d
|
Merge pull request #2464 from THUzyt21/Deploy-text-model-in-server
[Server]Deploy text model in server
|
2 years ago |
ZapBird
|
7a13b35fe6
|
BytesIO类型时，要保证切到初始位置，这样多次读取才能够正常。比如__call__函数。 (#2484)
* BytesIO类型时，要保证切到初始位置，这样多次读取才能够正常。比如__call__函数。
__call__函数的参数audio_file为BytesIO类型时执行到self.preprocess(model, audio_file)会报错，需要判断audio_file为BytesIO类型时执行audio_file.seek(0)。
|
2 years ago |
|
tianhao zhang
|
5bbe6e9897
|
support u2pp cli and server, optimiz code of u2pp decode, test=asr
|
2 years ago |
|
Hui Zhang
|
bdf876ea7b
|
Merge branch 'develop' into u2pp_export
|
2 years ago |
Zhao Yuting
|
304dc2603c
|
Update text_engine.py
|
2 years ago |
|
Zhao Yuting
|
8c945c073d
|
Update application.yaml
|
2 years ago |
|
Zhao Yuting
|
b9693a0e8e
|
Update text_engine.py
|
2 years ago |
|
Zhao Yuting
|
8ecf6796f3
|
Update text_engine.py
|
2 years ago |
|
Hui Zhang
|
afda7ed7d1
|
remove useless code
|
2 years ago |
|
YangZhou
|
4841f94298
|
Merge pull request #2421 from THUzyt21/Deploy-fast-text-model-for-cli
[CLI]Deploy fast text model for cli
|
2 years ago |
|
Hui Zhang
|
b20bf7d5de
|
masked_fill by multiply, remove while
|
2 years ago |
|
Zhao Yuting
|
d2da7f50d2
|
Update text_engine.py
precommihted already
|
2 years ago |
|
Zhao Yuting
|
82f731c153
|
Update application.yaml
change model
|
2 years ago |
|
Hui Zhang
|
feb27e2a84
|
fuse linear kv
|
2 years ago |
|
Hui Zhang
|
3adb20b468
|
eliminate shape and slice
|
2 years ago |
|
Hui Zhang
|
46088c0a16
|
elimiate attn transpose
|
2 years ago |
|
Hui Zhang
|
f9e3eaa024
|
transpose in matmul
|
2 years ago |
|
Hui Zhang
|
3d7ca93861
|
bool type slice
|
2 years ago |
|
Hui Zhang
|
c2c8a662b1
|
refactor reshape
|
2 years ago |
|
Hui Zhang
|
6de81d74d9
|
elimiete cast dtype for bool op
|
2 years ago |
|
Hui Zhang
|
8e7a315e00
|
remove comment
|
2 years ago |
|
Hui Zhang
|
c4a5ae3825
|
eliminate mul
|
2 years ago |
|
Hui Zhang
|
b7388ce25a
|
eliminate useless unsqueese
|
2 years ago |
|
Hui Zhang
|
1a1ce92cb4
|
Merge pull request #2415 from Zth9730/u2++_decoder
[s2t] support bitransformer decoder
|
2 years ago |
TianYuan
|
52af86fcc3
|
fix ERNIE-SAT bug when edit the end of sentenses, test=doc (#2432)
|
2 years ago |
|
tianhao zhang
|
d3e5937591
|
support bitransformer decoder
|
2 years ago |
|
Hui Zhang
|
7382050e21
|
fix bug on win
|
2 years ago |
|
TianYuan
|
b14da765e8
|
frm random spk embedding in voice cloning, test=doc (#2429)
|
2 years ago |
|
Hui Zhang
|
d25871a7b0
|
format
|
2 years ago |
|
Hui Zhang
|
b10512eb0e
|
more config or u2pp
|
2 years ago |
|
Hui Zhang
|
00b2c1c8fb
|
fix forward attention decoder caller
|
2 years ago |
zhoupc2015
|
2ae0f66d0d
|
Solve "unknown format: 3" (#2422)
* Solve execute the following code with return wav:
iob = io.BytesIO(wav)
wave.open(iob, 'rb')
will throw an "unknown format: 3" exception
|
2 years ago |
|
Hui Zhang
|
309c8d70d9
|
add reverse weight
|
2 years ago |
|
Hui Zhang
|
9b66680ea4
|
Merge branch 'u2++_decoder' into u2pp_export
|
2 years ago |
|
tianhao zhang
|
027535dec1
|
support bitransformer decoder, test=asr
|
2 years ago |
THUzyt21
|
bdbacd4249
|
precomited
|
2 years ago |
|
Zhao Yuting
|
d5dec46336
|
Update README.md
|
2 years ago |
|
Zhao Yuting
|
18b71dc136
|
Update README.md
|
2 years ago |
|
tianhao zhang
|
0a95689461
|
support bitransformer decoder
|
2 years ago |
|
tianhao zhang
|
455379b88e
|
support bitransformer decoder
|
2 years ago |
|
Zhao Yuting
|
a63a0b1350
|
Update pretrained_models.py
|
2 years ago |
|
Zhao Yuting
|
12a11394bd
|
Update infer.py
add a new faster model to infer in cli
|
2 years ago |
|
Zhao Yuting
|
fb7f04e021
|
Update README.md
|
2 years ago |
|
Zhao Yuting
|
92d09d5cce
|
Update README_cn.md
|
2 years ago |
|
Zhao Yuting
|
57dcd0d17f
|
Update infer.py
change the infer in order to implement the new faster model for text
|
2 years ago |
|
Zhao Yuting
|
b627666ce9
|
Update model_alias.py
Add a new model for faster text process in cli
|
2 years ago |
|
Zhao Yuting
|
a02654660a
|
Update pretrained_models.py
Add a new model for faster text process
|
2 years ago |
|
tianhao zhang
|
ecbf324286
|
support bitransformer decoder, test=asr
|
2 years ago |
|
tianhao zhang
|
1a56a6e42b
|
add bitransformer decoder, test=asr
|
2 years ago |
|
Hui Zhang
|
53d6baff0b
|
format
|
2 years ago |
|
Hui Zhang
|
549d477592
|
fix code style
|
2 years ago |
|
Hui Zhang
|
4d5cfd4003
|
export param from cnofig
|
2 years ago |
|
Hui Zhang
|
e3298c79ce
|
Merge branch 'develop' into u2_export
|
2 years ago |
|
Hui Zhang
|
260752aa2a
|
using forward_attention_decoder
|
2 years ago |
|
TianYuan
|
5e714ecb4a
|
[doc]update api docs (#2406)
* update apt docs, test=doc
|
2 years ago |
|
TianYuan
|
eac362057c
|
add typehint for g2pw (#2390)
|
2 years ago |
|
Hui Zhang
|
0d7d87120b
|
simplify feature pipeline graph
|
2 years ago |
WongLaw
|
324b166c52
|
Removed useless spk_id in speech_server and streaming_tts_server from demos, and support bilingual server engine, test=tts (#2380)
* Removed useless spk_id in speech_server and streaming_tts_server from demos, and support bilingual server engine.
|
2 years ago |
|
TianYuan
|
80b180217d
|
[TTS] fix some bugs of ERNIE-SAT (#2378)
* fix ernie_sat, test=tts
* fix for comments, test=tts
|
2 years ago |
|
Hui Zhang
|
8690a00bd8
|
add feature pipeline layer(cmvn, fbank), but to_static and jit.layer output is not equal
|
2 years ago |
|
Hui Zhang
|
07f566e0a5
|
Merge pull request #2372 from Zth9730/fix_dp_init
[s2t] DataParallel init method changed, fixed conformer could not multi-gpu training and don't affect dy2st
|
2 years ago |
|
Hui Zhang
|
3a8869fba4
|
rm to_static decarator; configure jit save for ctc_activation
|
2 years ago |
|
Hui Zhang
|
1c9f238ba0
|
configurable export
|
2 years ago |
|
Hui Zhang
|
63aeb747b0
|
more comment
|
2 years ago |
|
Hui Zhang
|
a7c6c54e75
|
fix
|
2 years ago |
|
Hui Zhang
|
d638325c46
|
do not jit save forward; using slice for zeros([0,0,0,0]) tensor
|
2 years ago |
|
tianhao zhang
|
663e3ab58e
|
fix dp init
|
2 years ago |
|
tianhao zhang
|
6745e9dd6b
|
fix dp init
|
2 years ago |
|
tianhao zhang
|
598eb1a5ef
|
Merge branch 'develop' into fix_dp_init
|
2 years ago |
|
WongLaw
|
989b755e8e
|
Revised must_neural_tone_words, test=doc. (#2370)
* Revised must_neural_tone_words.
|
2 years ago |
|
tianhao zhang
|
9560d650db
|
fix dp init
|
2 years ago |
|
TianYuan
|
7e4f3b029c
|
Merge pull request #2359 from yt605155624/add_vc2
[TTS]add aishell3 voice cloning with ECAPA-TDNN spk encoder
|
2 years ago |
|
tianhao zhang
|
82e04d7815
|
fix trianer
|
2 years ago |
|
TianYuan
|
f7873773bf
|
uadd __init__.py for VITS, test=tts (#2362)
|
2 years ago |
|
TianYuan
|
35c6ffa90b
|
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into add_vc2
|
2 years ago |
|
TianYuan
|
e622f42d92
|
add aishell3 voice cloning with ECAPA-TDNN spk encoder
|
2 years ago |
|
TianYuan
|
1c30cff1bf
|
fix gpus of ernie_sat, test=tts (#2355)
|
2 years ago |
|
Hui Zhang
|
2bb40c41ba
|
Merge pull request #2351 from Zth9730/fix_deepspeech
[s2t] fix deepspeech2 decode_wav
|
2 years ago |
|
tianhao zhang
|
ab92e2c98c
|
fix deepspeech2 decode_wav
|
2 years ago |
艾梦
|
ea9ee93739
|
[TTS]Update VITS to support VITS and its voice cloning training on AIShell-3 (#2268)
* code for training vits voice clone on aishell3.
Co-authored-by: TianYuan <white-sky@qq.com>
|
2 years ago |
|
TianYuan
|
795eb7bd10
|
format paddlespeech with pre-commit (#2331)
|
2 years ago |
|
TianYuan
|
5d5888af8e
|
fix tone, update readme (#2335)
|
2 years ago |
贾晓
|
0b544ee84e
|
Merge pull request #2336 from Zth9730/fix_multigpu_train
[s2t] fix format test=asr
|
2 years ago |
|
tianhao zhang
|
cdcb1a5316
|
s2t: fix encoder.py
|
2 years ago |
|
tianhao zhang
|
ed2819d7af
|
fix format test=asr
|
2 years ago |
|
Hui Zhang
|
58ab7e8d10
|
Merge pull request #2334 from Zth9730/fix_multigpu_train
[s2t] fix asr_engine.py
|
2 years ago |
|
tianhao zhang
|
1dfca4ef73
|
fix multigpu training
|
2 years ago |
|
Hui Zhang
|
94e750c4c4
|
Merge pull request #2327 from Zth9730/fix_multigpu_train
[s2t] fix conformer/transformer multi-gpu training, maybe impact dy2st
|
2 years ago |
|
tianhao zhang
|
ed80b0e2c3
|
fix multigpu training test=asr
|
2 years ago |
