96d76c83ad
multi-spk tts static model ( #2779 )
...
* updata readme, test=doc
* update yaml and readme, test=tts
* fix batch_size, test=tts
* update readme, test=doc
* chmod, test=tts
* add multi-spk tts static model infer on server, test=tts
3 years ago
2e51e0da90
[TTS]Fix attention bugs and sort VITS data with feats_lengths ( #2770 )
3 years ago
6725bcd823
revise paddlenlp's version ( #2767 )
3 years ago
979bbd9dcb
add mkldnn and trt config for paddleInference ( #2748 )
3 years ago
a8a240d4ef
remove paddle.fluid ( #2740 )
3 years ago
12fa8a2d19
[audio]patch:fix tensor_utils error ( #2738 )
...
* fix tensor utils
3 years ago
3f6afc4834
[TTS]Add slim for TTS ( #2729 )
3 years ago
42ff946007
[audio] mv paddlespeech/audio to paddleaudio ( #2706 )
...
* split paddlespeech/audio to paddleaudio.
* add sox io ,sox effect, kaldi native fbank to paddleaudio.
3 years ago
a874d8f325
Add prosody prediction in synthesize_e2e, test=tts ( #2693 )
3 years ago
62357d876c
[TTS]rm paddlelite in setup.py ( #2713 )
...
* rm paddlelite in setup.py
* fix setup.py
3 years ago
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
3 years ago
bd01bc155d
add greek char and fix issue2571 ( #2683 )
...
Co-authored-by: TianYuan <white-sky@qq.com>
3 years ago
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
3 years ago
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
3 years ago
b71f1428c7
add all whisper model size support, test=asr ( #2677 )
...
* add all whisper model size support
* add choices in parser.
3 years ago
0b4cf2211d
[TTS]Add TTS Paddle-Lite x86 inference ( #2667 )
...
* Add export2lite, test=tts
* add tts paddlelite x86 inference, test=tts
* update released_model.md, test=tts
* add paddlelite in setup.py
* update
3 years ago
1c3d2cb89e
add double byte char for zh normalization ( #2661 )
3 years ago
94a487bd81
[ASR] support wav2vec2 command line and demo ( #2658 )
...
* wav2vec2_cli
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* Update RESULTS.md
* Update RESULTS.md
* Update base_commands.py
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
* wav2vec2 demo update: support different optimizer and lr_schedular, align mdoel, update input type, test=asr
3 years ago
b1d3f59bcb
[s2t] add whisper asr large model ( #2640 )
...
* add whisper asr large model decoding, test=asr
* fix code style.
* fix json code style.
* remove resource and fix code style.
* fix yapf
* add cli and demos, fix some code style.
* fix some problem by comment.
* fix yapf
3 years ago
dc9d3baf51
Update onnx_api.py ( #2664 )
3 years ago
25b6bf9668
[tts] Add male voice for tts ( #2660 )
3 years ago
8d3494320d
[ASR] wav2vec2_en, test=asr ( #2637 )
...
* wav2vec2_en, test=asr
* wav2vec2_en, test=asr
* wav2vec2_en, test=asr
3 years ago
b7312e9f0b
Revised TN qualifier for measure notation, test=tts ( #2629 )
3 years ago
e6d20888c5
支持0维Tensor需要的修改 ( #2621 )
3 years ago
8a5fe83e1d
add ssml sentences.txt ( #2620 )
3 years ago
2c34481ea0
[s2t] quant with wav scp ( #2568 )
...
* add quant hint
* add paddleslim
* using paddleslim 2.3.4 and paddle 2.4
3 years ago
8d3464c050
[s2t] Update wav2vec2 license ( #2600 )
3 years ago
e18170228c
[tts] add adversarial loss ( #2588 )
3 years ago
9aab706cba
fix frontend bug, test=tts ( #2606 )
3 years ago
e348aa825d
Added Rhythm Prediction, test=tts
3 years ago
b96fb1d57e
Added Rythm Prediction, test=tts
3 years ago
d27364d141
Added Text Rhythm Prediction, test=tts
3 years ago
872be9c8ce
Merge branch 'PaddlePaddle:develop' into rhy
3 years ago
bbf2401e3e
Merge pull request #2524 from zh794390558/u2
...
[speechx] add u2/u2pp asr inference
3 years ago
72bbabbf79
Revised structure of rhythm prediction, test=tts
3 years ago
ed0138c6e3
add condition check if a ssml input and filter space line, test=tts
3 years ago
21cce0e0bb
Merge branch 'PaddlePaddle:develop' into hongliang1014
3 years ago
63c80121e2
fix uvicorn's bug
3 years ago
2a60c3d854
Merge pull request #2554 from dahu1/develop
...
标点恢复代码更新，test=asr
3 years ago
3ac7ac253f
fix review issue,test=tts
3 years ago
0476e645aa
Merge branch 'PaddlePaddle:develop' into hongliang1014
3 years ago
68134c8436
fix u2pp model ( #2549 )
3 years ago
cb76e66401
1.token配置不写死，2.text显示不乱码, test=asr
3 years ago
eac545e1db
Merge pull request #2544 from Zth9730/fix_attention
...
[s2t] fix attention eval bug, do not compose kv in infer
3 years ago
1ea828c30e
fix attention val bug
3 years ago
103e46f819
Merge branch 'PaddlePaddle:develop' into hongliang1014
3 years ago
2d71577e75
fix g2p ( #2539 )
3 years ago
f295d2d445
remove useless code
3 years ago
89e9ea69eb
modify __init__
3 years ago
1067088deb
modify __init__
3 years ago
f56cc08b18
add license content, test=tts
3 years ago
29508f400b
to fix CI issue, test=tts
3 years ago
60801d8f14
Merge branch 'hongliang1014' of https://github.com/david-95/PaddleSpeech into hongliang1014
3 years ago
ce21f9bc41
Merge branch 'PaddlePaddle:develop' into hongliang1014
3 years ago
278c7a41a8
add module define to fix ci, test=tts
3 years ago
964c22c677
Merge pull request #2532 from Zth9730/wav2vec2.0
...
[s2t] fix wav2vec2 report loss bug
3 years ago
86f65f0b8e
fix wav2vec2 report loss bug
3 years ago
13a7fa9808
enable chinese words' pinyin specified in text of ssml formats, test=tts
3 years ago
f1ca564731
Merge pull request #2518 from Zth9730/wav2vec2.0
...
[ASR] wav2vec2 ASR, pre-trained wav2vec2 based CTC for librispeech
3 years ago
2ae94bd277
freeze wav2vec2=True, change loss report and update README.md
3 years ago
3d994f5c23
format wav2vec2 demo
3 years ago
c6f9764ed6
Merge pull request #2510 from Zth9730/u2pp_jit_export
...
[s2t] use reverse_weight in decode.yaml
3 years ago
19180d359d
format wav2vec2 demo
3 years ago
6e429f0513
support wav2vec2ASR on librispeech
3 years ago
290c23b9d7
add u2 nnet, u2 nnet main, codelab, and can compile
3 years ago
e367242765
update dependency of paddle
3 years ago
5a66a14659
fix u2pp model version number
3 years ago
cda440e6f0
use reverse_weight in decode.yaml
3 years ago
c9b0c96b7b
Merge pull request #2502 from zh794390558/u2pp_export
...
[s2t] streaming conformer u2 and u2pp jit export
3 years ago
c98b5dd173
fix masked_fill which will nan in trainning
3 years ago
9277fcb8a8
fix attn can not train
3 years ago
1f4f98b171
fix bug
3 years ago
0359c3f6b5
Fix mix front ( #2493 )
...
* update mix frontend, test=tts
3 years ago
e86337a423
fix bug
3 years ago
925abcca23
format
3 years ago
2a75405e9a
Merge branch 'develop' into u2pp_export
3 years ago
3ed24474d2
wenetspeech asr1 quant
3 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)
3 years ago
5b5167b586
support u2pp cli and server, optimiz code of u2pp decode, test=asr
3 years ago
3507829a6d
Merge pull request #2464 from THUzyt21/Deploy-text-model-in-server
...
[Server]Deploy text model in server
3 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)。
3 years ago
5bbe6e9897
support u2pp cli and server, optimiz code of u2pp decode, test=asr
3 years ago
bdf876ea7b
Merge branch 'develop' into u2pp_export
3 years ago
304dc2603c
Update text_engine.py
3 years ago
8c945c073d
Update application.yaml
3 years ago
b9693a0e8e
Update text_engine.py
3 years ago
8ecf6796f3
Update text_engine.py
3 years ago
afda7ed7d1
remove useless code
3 years ago
4841f94298
Merge pull request #2421 from THUzyt21/Deploy-fast-text-model-for-cli
...
[CLI]Deploy fast text model for cli
3 years ago
b20bf7d5de
masked_fill by multiply, remove while
3 years ago
d2da7f50d2
Update text_engine.py
...
precommihted already
3 years ago
82f731c153
Update application.yaml
...
change model
3 years ago
feb27e2a84
fuse linear kv
3 years ago
3adb20b468
eliminate shape and slice
3 years ago
46088c0a16
elimiate attn transpose
3 years ago
f9e3eaa024
transpose in matmul
3 years ago
3d7ca93861
bool type slice
3 years ago
c2c8a662b1
refactor reshape
3 years ago
6de81d74d9
elimiete cast dtype for bool op
3 years ago
8e7a315e00
remove comment
3 years ago
c4a5ae3825
eliminate mul
3 years ago
b7388ce25a
eliminate useless unsqueese
3 years ago
1a1ce92cb4
Merge pull request #2415 from Zth9730/u2++_decoder
...
[s2t] support bitransformer decoder
3 years ago
52af86fcc3
fix ERNIE-SAT bug when edit the end of sentenses, test=doc ( #2432 )
3 years ago
d3e5937591
support bitransformer decoder
3 years ago
7382050e21
fix bug on win
3 years ago
b14da765e8
frm random spk embedding in voice cloning, test=doc ( #2429 )
3 years ago
d25871a7b0
format
3 years ago
b10512eb0e
more config or u2pp
3 years ago
00b2c1c8fb
fix forward attention decoder caller
3 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
3 years ago
309c8d70d9
add reverse weight
3 years ago
9b66680ea4
Merge branch 'u2++_decoder' into u2pp_export
3 years ago
027535dec1
support bitransformer decoder, test=asr
3 years ago
bdbacd4249
precomited
3 years ago
d5dec46336
Update README.md
3 years ago
18b71dc136
Update README.md
3 years ago
0a95689461
support bitransformer decoder
3 years ago
455379b88e
support bitransformer decoder
3 years ago
a63a0b1350
Update pretrained_models.py
3 years ago
12a11394bd
Update infer.py
...
add a new faster model to infer in cli
3 years ago
fb7f04e021
Update README.md
3 years ago
92d09d5cce
Update README_cn.md
3 years ago
57dcd0d17f
Update infer.py
...
change the infer in order to implement the new faster model for text
3 years ago
b627666ce9
Update model_alias.py
...
Add a new model for faster text process in cli
3 years ago
a02654660a
Update pretrained_models.py
...
Add a new model for faster text process
3 years ago
ecbf324286
support bitransformer decoder, test=asr
3 years ago
1a56a6e42b
add bitransformer decoder, test=asr
3 years ago
53d6baff0b
format
3 years ago
549d477592
fix code style
3 years ago
4d5cfd4003
export param from cnofig
3 years ago
e3298c79ce
Merge branch 'develop' into u2_export
3 years ago
260752aa2a
using forward_attention_decoder
3 years ago
5e714ecb4a
[doc]update api docs ( #2406 )
...
* update apt docs, test=doc
3 years ago
eac362057c
add typehint for g2pw ( #2390 )
3 years ago
0d7d87120b
simplify feature pipeline graph
3 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.
3 years ago
80b180217d
[TTS] fix some bugs of ERNIE-SAT ( #2378 )
...
* fix ernie_sat, test=tts
* fix for comments, test=tts
3 years ago
8690a00bd8
add feature pipeline layer(cmvn, fbank), but to_static and jit.layer output is not equal
3 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
3 years ago
3a8869fba4
rm to_static decarator; configure jit save for ctc_activation
3 years ago
1c9f238ba0
configurable export
3 years ago
63aeb747b0
more comment
3 years ago
a7c6c54e75
fix
3 years ago
d638325c46
do not jit save forward; using slice for zeros([0,0,0,0]) tensor
3 years ago
663e3ab58e
fix dp init
3 years ago
6745e9dd6b
fix dp init
3 years ago
598eb1a5ef
Merge branch 'develop' into fix_dp_init
3 years ago
989b755e8e
Revised must_neural_tone_words, test=doc. ( #2370 )
...
* Revised must_neural_tone_words.
3 years ago
9560d650db
fix dp init
3 years ago
7e4f3b029c
Merge pull request #2359 from yt605155624/add_vc2
...
[TTS]add aishell3 voice cloning with ECAPA-TDNN spk encoder
3 years ago
82e04d7815
fix trianer
3 years ago
f7873773bf
uadd __init__.py for VITS, test=tts ( #2362 )
3 years ago
35c6ffa90b
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into add_vc2
3 years ago
e622f42d92
add aishell3 voice cloning with ECAPA-TDNN spk encoder
3 years ago
1c30cff1bf
fix gpus of ernie_sat, test=tts ( #2355 )
3 years ago
2bb40c41ba
Merge pull request #2351 from Zth9730/fix_deepspeech
...
[s2t] fix deepspeech2 decode_wav
3 years ago
ab92e2c98c
fix deepspeech2 decode_wav
3 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>
3 years ago
795eb7bd10
format paddlespeech with pre-commit ( #2331 )
3 years ago
5d5888af8e
fix tone, update readme ( #2335 )
3 years ago
0b544ee84e
Merge pull request #2336 from Zth9730/fix_multigpu_train
...
[s2t] fix format test=asr
3 years ago
cdcb1a5316
s2t: fix encoder.py
3 years ago
ed2819d7af
fix format test=asr
3 years ago
58ab7e8d10
Merge pull request #2334 from Zth9730/fix_multigpu_train
...
[s2t] fix asr_engine.py
3 years ago
1dfca4ef73
fix multigpu training
3 years ago
94e750c4c4
Merge pull request #2327 from Zth9730/fix_multigpu_train
...
[s2t] fix conformer/transformer multi-gpu training, maybe impact dy2st
3 years ago
ed80b0e2c3
fix multigpu training test=asr
3 years ago
733ec7f2bc
fix conformer multi-gpu training test=asr
3 years ago
f5367f5efb
[TTS]fix bug of tone modify ( #2323 )
...
* add special tone modifed case
Co-authored-by: TianYuan <white-sky@qq.com>
3 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
3 years ago
7b864e8f38
clean old ernie sat inference scripts ( #2316 )
3 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
3 years ago
c9de22eaa8
[TN] Update quantifiers ( #2308 )
3 years ago
d1c70a7809
fix g2pw model ( #2304 )
3 years ago
043b21d3b4
fix mix frontend, test=tts ( #2299 )
3 years ago
25b96405df
add chinese words correct phonic,test=tts ( #2300 )
3 years ago
c1d4551055
add ernie sat synthesize_e2e, test=tts ( #2287 )
3 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
3 years ago
3f9339edff
Update polyphonic.yaml
3 years ago
f9a6970a62
Merge pull request #2263 from oyjxer/pc
...
[TTS]add ernie-sat sampler
3 years ago
677e0961a8
fix point bug, test=tts
3 years ago
4a59702d60
Merge pull request #2255 from lym0302/develop
...
[tts] fix point bug
3 years ago
0baec4325a
fix stats bugs
3 years ago
f7780658db
fix tone sand_hi bugs for Chinese frontend
3 years ago
b9be2bd64a
add ernie-sat sampler
3 years ago
f8f73e41f0
fix point bug, test=tts
3 years ago
5de2c2dab5
format g2pw
3 years ago
5d515f3f3f
update mix tts
3 years ago
a75b2a5bab
Merge pull request #2230 from BarryKCL/develop_g2pW
...
Add g2pW to Chinese frontend
3 years ago
db89cfe829
Merge pull request #2234 from lym0302/mix_example
...
[tts] add zh_en mix example
3 years ago
8dbefc0165
fix preprocess bug, add hifigan_csmsc decoder, update readme
3 years ago
a84b40ef79
update g2pW dict
3 years ago
d02e04d532
Update audio_handler.py
3 years ago
6593c24968
set window_size None
3 years ago
5e63ac1e60
Fix a bug in g2pW
3 years ago
0eb598b876
Merge pull request #2235 from david-95/hongliang-dev
...
add filter for double punctuation in sentences; add homonym, test=tts
3 years ago
0df7fc8fbf
remove comment
3 years ago
7ba74f175f
remove comment
3 years ago
f52a87b8d0
remove useless fix, test=tts
3 years ago
a48e4f249f
add filter for double punctuation, revise comment ;
...
add homonym, fix mistakes
3 years ago
aecf8fd384
add onnxruntime sess_options
3 years ago
368e3e1b59
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into mix_example
3 years ago
894556f871
add zh_en mix example, test=tts
3 years ago
1edd474bcb
add filter for double punctuation in sentences; add homonym, test=tts
3 years ago
61dd92e49c
update
3 years ago
de0f99150a
change G2PWModel download
3 years ago
744ea44279
add comment
3 years ago
7b0f2a796d
change transformers to paddlenlp.transformers
3 years ago
e60a63fbdd
Rollback "get_input_ids"
3 years ago
ab2a1219c8
Add g2pW to Chinese frontend
3 years ago
2f9bdf2306
Merge pull request #2222 from yt605155624/add_onnx_cli
...
[CLI]add onnxruntime infer for cli
3 years ago
c3d47441cf
fix fs bug in inference.py (change fixed 24000 to variable for ljspeech)
3 years ago
8da993bbf8
fix fs bug
3 years ago
788a3062d0
fix onnx am_ckpt from list to item in prtrained_mdoels.py
3 years ago
c6b25c05f4
change logger.debug to logger.info for streaming asr
3 years ago
c1fbfe928e
add test
3 years ago
cd662a08e0
fix for load specified model files
3 years ago
b9ade18055
add onnxruntime infer for cli
3 years ago
05bc258833
update docstring
3 years ago
6149daa221
export ctc_activation
3 years ago
923b0b873e
fix import kws.exps.mdtc
3 years ago
060e337623
fix dataloader factory, test=asr
3 years ago
b0b3222f9a
Merge pull request #2213 from yt605155624/fix_name_bug
...
[server]fix readme, test=doc
3 years ago
354601d0e9
fix readme, test=doc
3 years ago
812d80ab1c
Merge branch 'develop' of https://github.com/PaddlePaddle/DeepSpeech into u2_export
3 years ago
e5a6c243f1
fix jit save for conformer
3 years ago
510e240c5c
achange default voc in cli from pwgan_csmsc to hifigan_csmsc, test=tts
3 years ago
00e9853f66
add mix tts cli, test=tts
3 years ago
4e7106d9e2
Support dy2st
3 years ago
1f128a0817
Merge pull request #2117 from yt605155624/ernie_sat_trainer
...
[TTS]add ernie sat trainer
3 years ago
1bf78fa5c7
updatte batch_fn train.py, test=doc
3 years ago
9d4161ce5f
update config, test=doc
3 years ago
e1f8695456
add mix tts, test=tts
3 years ago
e2dc204d4d
update engine_warmup.py, test=tts
3 years ago
cf1b873528
update engine_warmup.py, test=tts
3 years ago
ef37f73a01
fix cnn cache dy2st shape
3 years ago
e21cceea51
Remove blank line
3 years ago
e6ac8881f1
Fix comments
3 years ago
ac680aa783
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into new_api
3 years ago
d098e027ca
Merge pull request #2155 from Jackwaterveg/develop_dev
...
[ASR] remove fluid（except gradclip）
3 years ago
294b7b00bd
Supprot dy2st for conformer
3 years ago
97965f4c37
fix mlm_prob, test=tts
3 years ago
7c9208765f
fix audio,test=doc
3 years ago
75997d8277
merge
3 years ago
72fa8176ca
fix for mix_lang
3 years ago
5503c8bd6b
add ernie_sat synthesize script for metadata.jsonl, test=tts
3 years ago
f4ac0c79d9
Merge pull request #2143 from lym0302/mix_front
...
[tts] add mix frontend
3 years ago
ae7a73bc11
Merge pull request #2138 from zh794390558/demos
...
[demos] more cli for speech demos
3 years ago
207bb5d93b
add mix frontend, test=tts
3 years ago
liangym
HuangLiangJie
TianYuan
zxcd
YangZhou
Zth9730
David An （An Hongliang）
kFoodie
Hui Zhang
dahu1
tianhao zhang
ZapBird
Zhao Yuting
zhoupc2015
THUzyt21
WongLaw
艾梦
贾晓
彭震东
李子
lym0302
pangchao04
BarryKCL
huangyuxin
0x45f
Betterman-qs
Jackwaterveg