BarryKCL
|
7b0f2a796d
|
change transformers to paddlenlp.transformers
|
2 years ago |
|
BarryKCL
|
e60a63fbdd
|
Rollback "get_input_ids"
|
2 years ago |
|
BarryKCL
|
ab2a1219c8
|
Add g2pW to Chinese frontend
|
2 years ago |
TianYuan
|
c3d47441cf
|
fix fs bug in inference.py (change fixed 24000 to variable for ljspeech)
|
2 years ago |
|
TianYuan
|
b9ade18055
|
add onnxruntime infer for cli
|
2 years ago |
|
TianYuan
|
1f128a0817
|
Merge pull request #2117 from yt605155624/ernie_sat_trainer
[TTS]add ernie sat trainer
|
2 years ago |
|
TianYuan
|
1bf78fa5c7
|
updatte batch_fn train.py, test=doc
|
2 years ago |
|
TianYuan
|
9d4161ce5f
|
update config, test=doc
|
2 years ago |
lym0302
|
e1f8695456
|
add mix tts, test=tts
|
2 years ago |
|
TianYuan
|
97965f4c37
|
fix mlm_prob, test=tts
|
2 years ago |
|
TianYuan
|
72fa8176ca
|
fix for mix_lang
|
2 years ago |
|
TianYuan
|
5503c8bd6b
|
add ernie_sat synthesize script for metadata.jsonl, test=tts
|
2 years ago |
|
lym0302
|
207bb5d93b
|
add mix frontend, test=tts
|
2 years ago |
|
TianYuan
|
028742b69a
|
update lr scheduler
|
2 years ago |
|
TianYuan
|
94688264c7
|
add ernie sat model file and config
|
2 years ago |
liangym
|
e153495519
|
Merge pull request #2122 from yt605155624/rm_server_log
[TTS]add stream_play_tts.py, test=doc
|
2 years ago |
|
TianYuan
|
6bbe6de1ec
|
add stream_play_tts.py, test=doc
|
2 years ago |
|
TianYuan
|
f6d1c545ac
|
fromat doc_string
|
2 years ago |
|
TianYuan
|
cf846f9ebc
|
rm extra log
|
2 years ago |
|
TianYuan
|
c0f126ecd9
|
fix int32 warning in tts, test=tts
|
2 years ago |
|
TianYuan
|
7743c6a1ff
|
add onnx models for aishell3/ljspeech/vctk's tts3/voc1/voc5, test=tts
|
2 years ago |
|
TianYuan
|
d1aa83a239
|
Merge pull request #2052 from yt605155624/ernie_sat
[TTS]add ernie sat inference
|
2 years ago |
|
TianYuan
|
79658a5f20
|
add ernie sat inference, test=tts
|
2 years ago |
|
TianYuan
|
02734141ce
|
Merge pull request #2040 from yt605155624/add_blank
[TTS]add blank between characters for vits
|
2 years ago |
|
TianYuan
|
1731976e4e
|
add blank between characters for vits, test=tts
|
2 years ago |
Hui Zhang
|
dfdf450b22
|
fix #2013; and format
|
2 years ago |
|
TianYuan
|
004ab8d0c0
|
reneame chunk to block in streaming tts, test=tts
|
3 years ago |
|
TianYuan
|
7bc54cbbe6
|
Merge pull request #1957 from yt605155624/vits_doc
[doc]add VITS readme, test=tts
|
3 years ago |
|
TianYuan
|
f9f014d159
|
add VITS readme, test=tts
|
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 |
|
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
|
c1b512c58a
|
rm fluid in tts, test=tts
|
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 |
|
TianYuan
|
8db06444c5
|
add vits trainer and synthesize
|
3 years ago |
|
TianYuan
|
e61757dbf7
|
fix yao, test=tts
|
3 years ago |
Jerryuhoo
|
167aaa65b9
|
normalize wav max value to 1 in preprocess, test=tts
|
3 years ago |
pollyyan
|
018dda6ee9
|
Merge pull request #1879 from QingshuChen/develop
speedyspeech support kunlun
|
3 years ago |
QingshuChen
|
e55177c3db
|
speedyspeech support kunlun
|
3 years ago |
root
|
9f389a7a33
|
support cpu, test=asr
|
3 years ago |
|
TianYuan
|
4b7786f2ed
|
add vits network scripts, test=tts
|
3 years ago |
|
Jerryuhoo
|
fba0693a20
|
fix random speaker embedding bug, test=tts
|
3 years ago |
|
lym0302
|
c6e6210964
|
code format, test=tts
|
3 years ago |
|
lym0302
|
88adcaa6dc
|
fix code, test=doc
|
3 years ago |
|
TianYuan
|
9121dfc046
|
Merge pull request #1752 from yt605155624/fix_wavernn
[TTS]fix wavernn white noise bug for paddle develop(2.3)
|
3 years ago |
|
TianYuan
|
08a4673355
|
fix wavernn bug, test=tts
|
3 years ago |
|
Hui Zhang
|
c7d9b11529
|
format
|
3 years ago |
|
TianYuan
|
4646f7cc8d
|
add paddle device set for ort and inference, test=doc
|
3 years ago |
|
TianYuan
|
c74fa9ada8
|
restructure syn_utils.py, test=tts
|
3 years ago |
|
TianYuan
|
dafe7c3657
|
add fastspeech2 cnndecoder onnx model, test=tts
|
3 years ago |
|
TianYuan
|
8bebf81199
|
[doc]fix typo, test=doc
|
3 years ago |
|
TianYuan
|
8b801ca18b
|
change NLC to NCL in speedyspeech, test=tts
|
3 years ago |
|
TianYuan
|
0282d45c62
|
remove fill_constant_batch_size_like in static model of speedyspeech, test=tts
|
3 years ago |
|
TianYuan
|
c765fca6b4
|
Merge branch 'develop' of github.com:PaddlePaddle/PaddleSpeech into add_onnx
|
3 years ago |
|
TianYuan
|
124eb6af8f
|
update notes, test=doc
|
3 years ago |
|
TianYuan
|
e0d222e674
|
update notes, test=doc
|
3 years ago |
|
TianYuan
|
f264b912fc
|
add warmup for frontend, test=doc
|
3 years ago |
|
TianYuan
|
7aecb2c4bb
|
add onnx inference for fastspeech2 + hifigan/mb_melgan, test=tts
|
3 years ago |
|
TianYuan
|
a8f5990869
|
fix preprocess bug, test=tts
|
3 years ago |
|
TianYuan
|
828ee14404
|
add license and reference for some models, test=doc
|
3 years ago |
|
TianYuan
|
3aec266ca5
|
add chunk size and pad size in args, test=doc
|
3 years ago |
|
TianYuan
|
4d7cd0e063
|
add streaming synthesize, test=tts
|
3 years ago |
|
TianYuan
|
005aa4066c
|
Merge branch 'develop' of github.com:PaddlePaddle/PaddleSpeech into cnn_decoder
|
3 years ago |
|
TianYuan
|
0fc79f474d
|
add CNNDecoder, test=tts
|
3 years ago |
|
TianYuan
|
bc5ae43d3a
|
restructure expand in length_regulator.py for paddle2onnx, test=tts
|
3 years ago |
|
TianYuan
|
5347dbad3f
|
fix dtype of window of stft, test=tts
|
3 years ago |
|
Hui Zhang
|
4051e7b762
|
fix compliance test bug, and format
|
3 years ago |
|
TianYuan
|
26ef47810d
|
Merge pull request #1593 from windstamp/npu_dev_20220322
[NPU] Add NPU support for TransformerTTS
|
3 years ago |
zhangkeliang
|
59b3de6a6d
|
[NPU] test TransformerTTS with NPU
|
3 years ago |
|
TianYuan
|
6469568d2a
|
update readme for vctk hifigan, test=tts
|
3 years ago |
|
TianYuan
|
5ab2601759
|
update readme for aishell3 hifigan, test=tts
|
3 years ago |
|
Hui Zhang
|
40ab05a462
|
Merge pull request #1552 from yt605155624/format_syn
[TTS]format synthesize
|
3 years ago |
|
TianYuan
|
544c372b50
|
fix cr, test=tts
|
3 years ago |
|
TianYuan
|
fe8bf2a38c
|
format synthesize, test=tts
|
3 years ago |
|
TianYuan
|
81d964f0a0
|
add vctk hifigan, test=tts
|
3 years ago |
|
TianYuan
|
175c39b4a4
|
Merge pull request #1511 from yt605155624/pre_fix_for_streaming
[TTS]add rtf for synthesize, add more vocoder for synthesize.sh
|
3 years ago |
|
Jerryuhoo
|
c116a3a926
|
fix Speedyspeech multi-speaker inference, test=tts
|
3 years ago |
|
TianYuan
|
cb07bd2a94
|
add rtf for synthesize, add more vocoder for synthesize_e2e.sh, test=tts
|
3 years ago |
|
Hui Zhang
|
e8f2d8f11b
|
Merge pull request #1507 from zh794390558/cli
[cli] add cli batch/pipe example to readme
|
3 years ago |
|
Hui Zhang
|
75098698d8
|
format,test=doc
|
3 years ago |
|
TianYuan
|
66a8beb27f
|
update text frontend, test=tts
|
3 years ago |
|
Hui Zhang
|
6b1fe70100
|
format code,test=doc
|
3 years ago |
|
TianYuan
|
67ec6242c3
|
fix ci for waveflow, test=tts
|
3 years ago |
|
TianYuan
|
f51097618b
|
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleSpeech into fix_ci_waveflow
|
3 years ago |
|
TianYuan
|
fc8c0e3ea2
|
fix ci for waveflow, test=tts
|
3 years ago |
|
Hui Zhang
|
718c849f68
|
Merge pull request #1445 from yt605155624/update_train
[TTS]init for all works in train.py when ngpu>1
|
3 years ago |
|
TianYuan
|
4ac7db185e
|
init for all works in train.py when ngpu>1, test=tts
|
3 years ago |
|
TianYuan
|
9699c00769
|
change the docstring style from numpydoc to google, test=tts
|
3 years ago |
|
TianYuan
|
683679bec7
|
merge data and datasets, test=tts
|
3 years ago |
|
TianYuan
|
7dc1f2daa3
|
fix some librosa bugs, test=tts
|
3 years ago |
|
TianYuan
|
25347bb6a3
|
rename tacotron2, test=tts
|
3 years ago |
|
Hui Zhang
|
dcfc32f1ec
|
Merge pull request #1379 from yt605155624/new_wavernn
[TTS] add wavernn
|
3 years ago |
|
TianYuan
|
0747600c95
|
[TTS]add ljspeech new tacotron2 (#1416)
* add ljspeech new tacotron2, test=tts
* update ljspeech waveflow's synthesize
* add config, test=doc
Co-authored-by: Hui Zhang <zhtclz@foxmail.com>
|
3 years ago |
|
TianYuan
|
348a1a33bf
|
update tacotron2 voice cloning in aishell3 with new tacotron2, test=tts (#1419)
|
3 years ago |
|
TianYuan
|
1b0c034134
|
update wavernn, test=tts
|
3 years ago |
|
TianYuan
|
89e69ee10e
|
[TTS]fix tacotron2 dygraph to static (#1414)
* fix tacotron2 dygraph to static , test=tts
* fix tacotron2 dygraph to static , test=tts
* simplify synthesize_e2e.py , test=tts
|
3 years ago |
huangyuxin
|
2a42421a63
|
cli add ds2-librispeech offline, fix versionm, test=asr
|
3 years ago |
|
TianYuan
|
001afee644
|
fix wavernn dygraph to static , test=tts
|
3 years ago |
