6a1fb158d9
format code with pre-commit
2021-05-13 16:22:56 +08:00
77eb13d95d
format code
2021-04-28 20:02:29 +08:00
2b62fbb614
1. change the default min value of LogMagnitude to 1e-5;
...
2. remove stop logit prediction from tacotron2 model.
2021-03-23 10:44:22 +08:00
f9d6160916
add an option to normalize volume when loading audio.
2021-03-22 21:38:28 +08:00
e03e96d9e4
format all the code with yapf
2020-12-20 13:15:07 +08:00
29cc759241
add access control by __all__ in modules
2020-12-09 15:58:39 +08:00
b65cc4d8dc
add Unit normalizer
2020-11-19 20:17:42 +08:00
c43216ae9b
1. API renaming Conv1d -> Conv1D, BatchNorm1d -> BatchNorm1D;
...
2. add losses in parakeet/modules;
3. fix a bug in phonetics;
4. TransformerTTS update: encoder dim can be different from decoder dim;
5. MultiHeadAttention in TransformerTTS: add k_input_dim & v_input_dim in __init__ to allow differemt feature sizes for k and v.
2020-10-22 05:04:45 +00:00
a8192c79cc
WIP: refactor
2020-10-10 15:51:54 +08:00
9d79699432
add license
2020-02-26 21:03:51 +08:00
47a618ce38
right fastspeech version.
2020-01-22 07:46:35 +00:00
e0aef2e081
rebuild code and TransformerTTS is right. FastSpeech will later.
2020-01-08 03:55:06 +00:00
9fe6ad11f0
Training with multi-GPU
2019-12-17 06:23:34 +00:00
chenfeiyu
iclementine
lifuchen