e6d20888c5
支持0维Tensor需要的修改 ( #2621 )
2 years ago
8a5fe83e1d
add ssml sentences.txt ( #2620 )
2 years ago
2c34481ea0
[s2t] quant with wav scp ( #2568 )
...
* add quant hint
* add paddleslim
* using paddleslim 2.3.4 and paddle 2.4
2 years ago
8d3464c050
[s2t] Update wav2vec2 license ( #2600 )
2 years ago
e18170228c
[tts] add adversarial loss ( #2588 )
2 years ago
9aab706cba
fix frontend bug, test=tts ( #2606 )
2 years ago
e348aa825d
Added Rhythm Prediction, test=tts
2 years ago
b96fb1d57e
Added Rythm Prediction, test=tts
2 years ago
d27364d141
Added Text Rhythm Prediction, test=tts
2 years ago
872be9c8ce
Merge branch 'PaddlePaddle:develop' into rhy
2 years ago
bbf2401e3e
Merge pull request #2524 from zh794390558/u2
...
[speechx] add u2/u2pp asr inference
2 years ago
72bbabbf79
Revised structure of rhythm prediction, test=tts
2 years ago
ed0138c6e3
add condition check if a ssml input and filter space line, test=tts
2 years ago
21cce0e0bb
Merge branch 'PaddlePaddle:develop' into hongliang1014
2 years ago
63c80121e2
fix uvicorn's bug
2 years ago
2a60c3d854
Merge pull request #2554 from dahu1/develop
...
标点恢复代码更新，test=asr
2 years ago
3ac7ac253f
fix review issue,test=tts
2 years ago
0476e645aa
Merge branch 'PaddlePaddle:develop' into hongliang1014
2 years ago
68134c8436
fix u2pp model ( #2549 )
2 years ago
cb76e66401
1.token配置不写死，2.text显示不乱码, test=asr
2 years ago
eac545e1db
Merge pull request #2544 from Zth9730/fix_attention
...
[s2t] fix attention eval bug, do not compose kv in infer
2 years ago
1ea828c30e
fix attention val bug
2 years ago
103e46f819
Merge branch 'PaddlePaddle:develop' into hongliang1014
2 years ago
2d71577e75
fix g2p ( #2539 )
2 years ago
f295d2d445
remove useless code
2 years ago
89e9ea69eb
modify __init__
2 years ago
1067088deb
modify __init__
2 years ago
f56cc08b18
add license content, test=tts
2 years ago
29508f400b
to fix CI issue, test=tts
2 years ago
60801d8f14
Merge branch 'hongliang1014' of https://github.com/david-95/PaddleSpeech into hongliang1014
2 years ago
ce21f9bc41
Merge branch 'PaddlePaddle:develop' into hongliang1014
2 years ago
278c7a41a8
add module define to fix ci, test=tts
2 years ago
964c22c677
Merge pull request #2532 from Zth9730/wav2vec2.0
...
[s2t] fix wav2vec2 report loss bug
2 years ago
86f65f0b8e
fix wav2vec2 report loss bug
2 years ago
13a7fa9808
enable chinese words' pinyin specified in text of ssml formats, test=tts
2 years ago
f1ca564731
Merge pull request #2518 from Zth9730/wav2vec2.0
...
[ASR] wav2vec2 ASR, pre-trained wav2vec2 based CTC for librispeech
2 years ago
2ae94bd277
freeze wav2vec2=True, change loss report and update README.md
2 years ago
3d994f5c23
format wav2vec2 demo
2 years ago
c6f9764ed6
Merge pull request #2510 from Zth9730/u2pp_jit_export
...
[s2t] use reverse_weight in decode.yaml
2 years ago
19180d359d
format wav2vec2 demo
2 years ago
6e429f0513
support wav2vec2ASR on librispeech
2 years ago
290c23b9d7
add u2 nnet, u2 nnet main, codelab, and can compile
2 years ago
e367242765
update dependency of paddle
2 years ago
5a66a14659
fix u2pp model version number
2 years ago
cda440e6f0
use reverse_weight in decode.yaml
2 years ago
c9b0c96b7b
Merge pull request #2502 from zh794390558/u2pp_export
...
[s2t] streaming conformer u2 and u2pp jit export
2 years ago
c98b5dd173
fix masked_fill which will nan in trainning
2 years ago
9277fcb8a8
fix attn can not train
2 years ago
1f4f98b171
fix bug
2 years ago
0359c3f6b5
Fix mix front ( #2493 )
...
* update mix frontend, test=tts
2 years ago
e86337a423
fix bug
2 years ago
925abcca23
format
2 years ago
2a75405e9a
Merge branch 'develop' into u2pp_export
2 years ago
3ed24474d2
wenetspeech asr1 quant
2 years ago
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
5b5167b586
support u2pp cli and server, optimiz code of u2pp decode, test=asr
2 years ago
3507829a6d
Merge pull request #2464 from THUzyt21/Deploy-text-model-in-server
...
[Server]Deploy text model in server
2 years ago
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
5bbe6e9897
support u2pp cli and server, optimiz code of u2pp decode, test=asr
2 years ago
bdf876ea7b
Merge branch 'develop' into u2pp_export
2 years ago
304dc2603c
Update text_engine.py
2 years ago
8c945c073d
Update application.yaml
2 years ago
b9693a0e8e
Update text_engine.py
2 years ago
8ecf6796f3
Update text_engine.py
2 years ago
afda7ed7d1
remove useless code
2 years ago
4841f94298
Merge pull request #2421 from THUzyt21/Deploy-fast-text-model-for-cli
...
[CLI]Deploy fast text model for cli
2 years ago
b20bf7d5de
masked_fill by multiply, remove while
2 years ago
d2da7f50d2
Update text_engine.py
...
precommihted already
2 years ago
82f731c153
Update application.yaml
...
change model
2 years ago
feb27e2a84
fuse linear kv
2 years ago
3adb20b468
eliminate shape and slice
2 years ago
46088c0a16
elimiate attn transpose
2 years ago
f9e3eaa024
transpose in matmul
2 years ago
3d7ca93861
bool type slice
2 years ago
c2c8a662b1
refactor reshape
2 years ago
6de81d74d9
elimiete cast dtype for bool op
2 years ago
8e7a315e00
remove comment
2 years ago
c4a5ae3825
eliminate mul
2 years ago
b7388ce25a
eliminate useless unsqueese
2 years ago
1a1ce92cb4
Merge pull request #2415 from Zth9730/u2++_decoder
...
[s2t] support bitransformer decoder
2 years ago
52af86fcc3
fix ERNIE-SAT bug when edit the end of sentenses, test=doc ( #2432 )
2 years ago
d3e5937591
support bitransformer decoder
2 years ago
7382050e21
fix bug on win
2 years ago
b14da765e8
frm random spk embedding in voice cloning, test=doc ( #2429 )
2 years ago
d25871a7b0
format
2 years ago
b10512eb0e
more config or u2pp
2 years ago
00b2c1c8fb
fix forward attention decoder caller
2 years ago
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
309c8d70d9
add reverse weight
2 years ago
9b66680ea4
Merge branch 'u2++_decoder' into u2pp_export
2 years ago
027535dec1
support bitransformer decoder, test=asr
2 years ago
bdbacd4249
precomited
2 years ago
d5dec46336
Update README.md
2 years ago
18b71dc136
Update README.md
2 years ago
0a95689461
support bitransformer decoder
2 years ago
455379b88e
support bitransformer decoder
2 years ago
a63a0b1350
Update pretrained_models.py
2 years ago
12a11394bd
Update infer.py
...
add a new faster model to infer in cli
2 years ago
fb7f04e021
Update README.md
2 years ago
92d09d5cce
Update README_cn.md
2 years ago
57dcd0d17f
Update infer.py
...
change the infer in order to implement the new faster model for text
2 years ago
b627666ce9
Update model_alias.py
...
Add a new model for faster text process in cli
2 years ago
a02654660a
Update pretrained_models.py
...
Add a new model for faster text process
2 years ago
ecbf324286
support bitransformer decoder, test=asr
2 years ago
1a56a6e42b
add bitransformer decoder, test=asr
2 years ago
53d6baff0b
format
2 years ago
549d477592
fix code style
2 years ago
4d5cfd4003
export param from cnofig
2 years ago
e3298c79ce
Merge branch 'develop' into u2_export
2 years ago
260752aa2a
using forward_attention_decoder
2 years ago
5e714ecb4a
[doc]update api docs ( #2406 )
...
* update apt docs, test=doc
2 years ago
eac362057c
add typehint for g2pw ( #2390 )
2 years ago
0d7d87120b
simplify feature pipeline graph
2 years ago
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
80b180217d
[TTS] fix some bugs of ERNIE-SAT ( #2378 )
...
* fix ernie_sat, test=tts
* fix for comments, test=tts
2 years ago
8690a00bd8
add feature pipeline layer(cmvn, fbank), but to_static and jit.layer output is not equal
2 years ago
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
3a8869fba4
rm to_static decarator; configure jit save for ctc_activation
2 years ago
1c9f238ba0
configurable export
2 years ago
63aeb747b0
more comment
2 years ago
a7c6c54e75
fix
2 years ago
d638325c46
do not jit save forward; using slice for zeros([0,0,0,0]) tensor
2 years ago
663e3ab58e
fix dp init
2 years ago
6745e9dd6b
fix dp init
2 years ago
598eb1a5ef
Merge branch 'develop' into fix_dp_init
2 years ago
989b755e8e
Revised must_neural_tone_words, test=doc. ( #2370 )
...
* Revised must_neural_tone_words.
2 years ago
9560d650db
fix dp init
2 years ago
7e4f3b029c
Merge pull request #2359 from yt605155624/add_vc2
...
[TTS]add aishell3 voice cloning with ECAPA-TDNN spk encoder
2 years ago
82e04d7815
fix trianer
2 years ago
f7873773bf
uadd __init__.py for VITS, test=tts ( #2362 )
2 years ago
35c6ffa90b
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into add_vc2
2 years ago
e622f42d92
add aishell3 voice cloning with ECAPA-TDNN spk encoder
2 years ago
1c30cff1bf
fix gpus of ernie_sat, test=tts ( #2355 )
2 years ago
2bb40c41ba
Merge pull request #2351 from Zth9730/fix_deepspeech
...
[s2t] fix deepspeech2 decode_wav
2 years ago
ab92e2c98c
fix deepspeech2 decode_wav
2 years ago
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
795eb7bd10
format paddlespeech with pre-commit ( #2331 )
2 years ago
5d5888af8e
fix tone, update readme ( #2335 )
2 years ago
0b544ee84e
Merge pull request #2336 from Zth9730/fix_multigpu_train
...
[s2t] fix format test=asr
2 years ago
cdcb1a5316
s2t: fix encoder.py
2 years ago
ed2819d7af
fix format test=asr
2 years ago
58ab7e8d10
Merge pull request #2334 from Zth9730/fix_multigpu_train
...
[s2t] fix asr_engine.py
2 years ago
1dfca4ef73
fix multigpu training
2 years ago
94e750c4c4
Merge pull request #2327 from Zth9730/fix_multigpu_train
...
[s2t] fix conformer/transformer multi-gpu training, maybe impact dy2st
2 years ago
ed80b0e2c3
fix multigpu training test=asr
2 years ago
733ec7f2bc
fix conformer multi-gpu training test=asr
2 years ago
f5367f5efb
[TTS]fix bug of tone modify ( #2323 )
...
* add special tone modifed case
Co-authored-by: TianYuan <white-sky@qq.com>
2 years ago
c28064fec2
Update asr_engine.py ( #2302 )
...
* Update asr_engine.py
* Update asr_engine.py
* Update application.yaml
must add parameter "num_decoding_left_chunks" so as to modify this in other scenarios.
* Update asr_engine.py
* Update application.yaml
* Update application.yaml
* Update asr_engine.py
2 years ago
7b864e8f38
clean old ernie sat inference scripts ( #2316 )
2 years ago
c7163abffa
add thanks into readme, append data for chinese unit ( #2312 )
...
* add chinese words correct phonic,test=tts
* added thanks into readme. add data of unit, test=tts
* added thanks into readme. add data of unit, test=tts
* modify data of unit, test=tts
* modify thanks, test=tts
2 years ago
c9de22eaa8
[TN] Update quantifiers ( #2308 )
2 years ago
d1c70a7809
fix g2pw model ( #2304 )
2 years ago
043b21d3b4
fix mix frontend, test=tts ( #2299 )
2 years ago
25b96405df
add chinese words correct phonic,test=tts ( #2300 )
2 years ago
c1d4551055
add ernie sat synthesize_e2e, test=tts ( #2287 )
2 years ago
5a58a27492
[TTS]指定G2PW的传入数据类型 , test=tts ( #2288 )
...
* fix ONNXRuntimeError Specify data type (int64),test=tts
* Tactron2→Tacotron2 ,test=doc
2 years ago
3f9339edff
Update polyphonic.yaml
2 years ago
f9a6970a62
Merge pull request #2263 from oyjxer/pc
...
[TTS]add ernie-sat sampler
2 years ago
677e0961a8
fix point bug, test=tts
2 years ago
4a59702d60
Merge pull request #2255 from lym0302/develop
...
[tts] fix point bug
2 years ago
0baec4325a
fix stats bugs
2 years ago
f7780658db
fix tone sand_hi bugs for Chinese frontend
2 years ago
b9be2bd64a
add ernie-sat sampler
2 years ago
f8f73e41f0
fix point bug, test=tts
2 years ago
5de2c2dab5
format g2pw
2 years ago
5d515f3f3f
update mix tts
2 years ago
a75b2a5bab
Merge pull request #2230 from BarryKCL/develop_g2pW
...
Add g2pW to Chinese frontend
2 years ago
db89cfe829
Merge pull request #2234 from lym0302/mix_example
...
[tts] add zh_en mix example
2 years ago
8dbefc0165
fix preprocess bug, add hifigan_csmsc decoder, update readme
2 years ago
a84b40ef79
update g2pW dict
2 years ago
d02e04d532
Update audio_handler.py
2 years ago
6593c24968
set window_size None
2 years ago
5e63ac1e60
Fix a bug in g2pW
2 years ago
0eb598b876
Merge pull request #2235 from david-95/hongliang-dev
...
add filter for double punctuation in sentences; add homonym, test=tts
2 years ago
0df7fc8fbf
remove comment
2 years ago
7ba74f175f
remove comment
2 years ago
f52a87b8d0
remove useless fix, test=tts
2 years ago
a48e4f249f
add filter for double punctuation, revise comment ;
...
add homonym, fix mistakes
2 years ago
aecf8fd384
add onnxruntime sess_options
2 years ago
368e3e1b59
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into mix_example
2 years ago
894556f871
add zh_en mix example, test=tts
2 years ago
1edd474bcb
add filter for double punctuation in sentences; add homonym, test=tts
2 years ago
61dd92e49c
update
2 years ago
de0f99150a
change G2PWModel download
2 years ago
744ea44279
add comment
2 years ago
7b0f2a796d
change transformers to paddlenlp.transformers
2 years ago
e60a63fbdd
Rollback "get_input_ids"
2 years ago
ab2a1219c8
Add g2pW to Chinese frontend
2 years ago
2f9bdf2306
Merge pull request #2222 from yt605155624/add_onnx_cli
...
[CLI]add onnxruntime infer for cli
2 years ago
c3d47441cf
fix fs bug in inference.py (change fixed 24000 to variable for ljspeech)
2 years ago
8da993bbf8
fix fs bug
2 years ago
788a3062d0
fix onnx am_ckpt from list to item in prtrained_mdoels.py
2 years ago
c6b25c05f4
change logger.debug to logger.info for streaming asr
2 years ago
c1fbfe928e
add test
2 years ago
cd662a08e0
fix for load specified model files
2 years ago
b9ade18055
add onnxruntime infer for cli
2 years ago
05bc258833
update docstring
2 years ago
6149daa221
export ctc_activation
2 years ago
923b0b873e
fix import kws.exps.mdtc
2 years ago
060e337623
fix dataloader factory, test=asr
2 years ago
Zth9730
David An （An Hongliang）
Hui Zhang
liangym
TianYuan
WongLaw
YangZhou
dahu1
tianhao zhang
ZapBird
Zhao Yuting
zhoupc2015
THUzyt21
WongLaw
艾梦
贾晓
彭震东
李子
lym0302
pangchao04
BarryKCL
huangyuxin