liuyibing01
|
cd59c98637
|
Merge branch 'master' of upstream
|
2020-02-29 03:26:59 +00:00 |
|
liuyibing01
|
b996e27f41
|
Temp fix bad get attr
|
2020-02-29 03:25:47 +00:00 |
chenfeiyu
|
44e61e0781
|
add missing parallel_wavenet, and fix python2 compatability
|
2020-02-28 03:24:24 +00:00 |
|
chenfeiyu
|
424c16a68d
|
staged clarinet
|
2020-02-27 10:23:05 +00:00 |
|
chenfeiyu
|
a012825423
|
refactor wavenet
|
2020-02-26 15:06:48 +00:00 |
lifuchen
|
9d79699432
|
add license
|
2020-02-26 21:03:51 +08:00 |
|
liuyibing01
|
737d142ae4
|
Enable the fp16 inference for waveflow
|
2020-02-25 15:53:54 +00:00 |
|
liuyibing01
|
8b051486f1
|
Update synthesis script for waveflow
|
2020-02-24 02:35:19 +00:00 |
|
liuyibing01
|
f9d9785211
|
Update waveflow to 1.7 api and verified training
|
2020-02-23 19:00:17 +00:00 |
lifuchen
|
47d78b8739
|
remove utils.py to models/transdformer_tts
|
2020-02-20 02:17:25 +00:00 |
|
chenfeiyu
|
2bde79514a
|
deepvoice3: update logging functionalities
|
2020-02-17 14:53:37 +00:00 |
|
chenfeiyu
|
70e271ed95
|
deepvoice3: fix a bug in position embedding, fix initialization details for converter and attention.
|
2020-02-17 05:48:43 +00:00 |
|
lifuchen
|
5ad005fd9a
|
move data.py and rename some files
|
2020-02-16 17:54:11 +00:00 |
|
chenfeiyu
|
173693f469
|
fix missing imports, fix ljspeech.yaml config key: encoder_channels
|
2020-02-16 17:54:11 +00:00 |
|
chenfeiyu
|
155dfe633d
|
add deepvoice3 model and example
|
2020-02-16 17:54:11 +00:00 |
|
lifuchen
|
04d7f8b598
|
transform parse to argparse
|
2020-02-13 06:48:21 +00:00 |
|
lifuchen
|
f5ac04b1a3
|
update Conv1D and Linear
|
2020-02-12 08:51:32 +00:00 |
|
lifuchen
|
6908ec520c
|
Adjust the directory structure
|
2020-02-11 08:57:30 +00:00 |
|
lifuchen
|
fc84ca2d4b
|
Adjust the directory structure
|
2020-02-11 08:56:28 +00:00 |
|
lifuchen
|
5b2d2a37c9
|
add TransformerTTS and fastspeech
|
2020-02-10 07:47:19 +00:00 |
|
lifuchen
|
185e25fedf
|
add transformerTTS and fastspeech
|
2020-02-10 07:38:29 +00:00 |
|
lifuchen
|
6068374a3c
|
modified fastspeech network
|
2020-02-06 09:11:28 +00:00 |
|
lifuchen
|
47a618ce38
|
right fastspeech version.
|
2020-01-22 07:46:35 +00:00 |
|
lifuchen
|
f009411b57
|
update fastspeech
|
2020-01-15 06:10:27 +00:00 |
|
lifuchen
|
ab0fe8f304
|
TransformerTTS precision alignment
|
2020-01-13 12:37:49 +00:00 |
|
lifuchen
|
ae88be3419
|
modified load checkpoint in train
|
2020-01-08 06:08:09 +00:00 |
|
lifuchen
|
e0aef2e081
|
rebuild code and TransformerTTS is right. FastSpeech will later.
|
2020-01-08 03:55:06 +00:00 |
|
lifuchen
|
5b632d18af
|
Merge branch 'master' of ssh://gitlab.baidu.com:8022/liuyibing01/Parakeet into add_TranTTS
|
2020-01-03 08:30:27 +00:00 |
|
lifuchen
|
2179d6d5b0
|
add FastSpeech
|
2020-01-03 08:25:17 +00:00 |
Kexin Zhao
|
91ab2b34c4
|
small change
|
2019-12-19 00:37:43 -08:00 |
|
zhaokexin01
|
4af577ad72
|
Update README.md
|
2019-12-19 16:34:22 +08:00 |
|
Kexin Zhao
|
0e18d60057
|
refine code
|
2019-12-19 00:03:06 -08:00 |
|
lifuchen
|
9fe6ad11f0
|
Training with multi-GPU
|
2019-12-17 06:23:34 +00:00 |
|
Kexin Zhao
|
8c22397b55
|
add working synthesis code
|
2019-12-16 16:42:39 -08:00 |
|
lifuchen
|
8a9bbc2634
|
add_TransformerTTS
|
2019-12-16 09:04:22 +00:00 |
|
Kexin Zhao
|
f6f0a2ca21
|
add documentation
|
2019-12-12 18:11:32 -08:00 |
|
Kexin Zhao
|
83d6a85b86
|
add waveflow model valid for training only
|
2019-12-12 17:58:10 -08:00 |
|
zhaokexin01
|
862e23164d
|
Update README.md
|
2019-12-04 06:42:27 +08:00 |
|
Kexin Zhao
|
98841ee48a
|
clean code
|
2019-12-02 22:58:17 -08:00 |
|
Kexin Zhao
|
b15c313423
|
working integraton with parakeet
|
2019-12-02 14:00:53 -08:00 |
|
chenfeiyu
|
5b63663aeb
|
folder adjust
|
2019-11-25 08:09:46 +00:00 |
|
chenfeiyu
|
ca7d1dddf3
|
fix import errors caused by moving files
|
2019-11-25 07:40:30 +00:00 |
|
chenfeiyu
|
de4c5d4f49
|
add models & modules back
|
2019-11-25 03:40:52 +00:00 |