iclementine
e03e96d9e4
format all the code with yapf
2020-12-20 13:15:07 +08:00
chenfeiyu
29cc759241
add access control by __all__ in modules
2020-12-09 15:58:39 +08:00
iclementine
49231ca8e5
move datasets
2020-11-19 22:04:25 +08:00
iclementine
abee3ecdd4
move datasets into parakeet.datasets
2020-11-19 20:31:21 +08:00
chenfeiyu
57d820f055
add support for channel last in batch_spec, and Conv1dBatchNorm
2020-10-30 15:13:57 +08:00
chenfeiyu
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
iclementine
6aa7af1aa4
add AudioFolderDataset
2020-10-15 23:15:27 +08:00
iclementine
53d0382fc7
clean code: remove deprecated modules
2020-10-15 23:07:30 +08:00
iclementine
a8192c79cc
WIP: refactor
2020-10-10 15:51:54 +08:00
chenfeiyu
6aac18278e
refactor for deep voice 3, update wavenet and clarinet to use enable_dygraph
2020-05-20 12:37:19 +00:00
chenfeiyu
6a9eab4b73
fix typos and refine doc
2020-03-09 15:33:13 +00:00
chenfeiyu
e0e40c5379
Merge branch 'master' of upstream.
2020-03-09 07:30:19 +00:00
chenfeiyu
4b2b974eb4
refine docstring for parakeet.data and deep voice 3, wavenet and clarinet
2020-03-09 03:06:28 +00:00
lifuchen
a302bf21f4
fix conflicts of dataset.py
2020-03-06 11:49:53 +00:00
chenfeiyu
86fff7a077
add doc for parakeet.data, python2 compatability for DataIterator and lazy CacheDataset
2020-03-06 02:55:42 +00:00
lifuchen
d08779d61e
Modified data.py to generate masks as models inputs
2020-03-05 07:22:50 +00:00
lifuchen
078d22e51c
Modified data.py to generate masks as models inputs
2020-03-05 07:08:12 +00:00
chenfeiyu
424c16a68d
staged clarinet
2020-02-27 10:23:05 +00:00
lifuchen
9d79699432
add license
2020-02-26 21:03:51 +08:00
chenfeiyu
78582dbecd
make DataIterator compatible for python 2
2020-02-24 06:54:57 +00:00
chenfeiyu
173693f469
fix missing imports, fix ljspeech.yaml config key: encoder_channels
2020-02-16 17:54:11 +00:00
lifuchen
d0015239db
Eliminated conflict
2020-02-07 01:07:51 +00:00
chenfeiyu
837749a32c
update statset and datacargo's design
2020-02-06 15:40:04 +08:00
lifuchen
9fe6ad11f0
Training with multi-GPU
2019-12-17 06:23:34 +00:00
lifuchen
8a9bbc2634
add_TransformerTTS
2019-12-16 09:04:22 +00:00
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
5bd396712c
fix sampler length
2019-11-25 10:47:31 +00:00
chenfeiyu
34bd1e984d
add setup.py
2019-11-22 11:32:59 +08:00
chenfeiyu
617605c8fe
place parakeet into Parakeet/parakeet, and add tests
2019-11-21 23:02:32 +08:00