Commit Graph

476 Commits

Author SHA1 Message Date
iclementine 49231ca8e5 move datasets 2020-11-19 22:04:25 +08:00
iclementine db7598c702 add datasets 2020-11-19 20:43:03 +08:00
iclementine abee3ecdd4 move datasets into parakeet.datasets 2020-11-19 20:31:21 +08:00
iclementine b65cc4d8dc add Unit normalizer 2020-11-19 20:17:42 +08:00
iclementine a01200e437 add an cli for cloning examples 2020-11-19 18:08:11 +08:00
iclementine c7e5aaa540 remove old examples 2020-11-19 15:47:57 +08:00
iclementine 0e35119453 add more doc in chinese 2020-11-19 10:41:37 +08:00
iclementine c8622b4699 update experiment guide 2020-11-17 16:33:13 +08:00
iclementine e470cda881 add Chinese docs 2020-11-17 10:48:02 +08:00
iclementine 01f30d7cc8 switch to markdown 2020-11-12 17:28:07 +08:00
iclementine 7822a89fec add doctree 2020-11-12 17:17:02 +08:00
iclementine 098d3795c2 add documentation for installation. 2020-11-12 17:07:03 +08:00
chenfeiyu a9177cd6c2 waveflow: explicitly call forward hook before calling a method other than forward when needed. 2020-11-09 15:46:27 +08:00
chenfeiyu af4da7dd9e 1. update code for waveflow's probability density estimation and sampling;
2. add WaveFlowLoss.
2020-11-04 23:22:45 +08:00
chenfeiyu e07441c193 waveflow refactor: add prediction functionalities 2020-11-04 19:31:36 +08:00
chenfeiyu 8094578f6d update waveflow to 2.0 APIs 2020-11-04 01:37:49 +08:00
chenfeiyu 0cdad602e2 fix a bug for changing reduction factor in transformner_tts 2020-11-03 11:18:46 +08:00
chenfeiyu 1f71f65c28 Merge branch 'reborn' into exp 2020-10-30 21:44:06 +08:00
chenfeiyu 68f5e1de15 add utility to pack attention weights 2020-10-30 21:36:11 +08:00
chenfeiyu 45d6f3b99d specify a U(-.05, .05) initializer for Embedding 2020-10-30 17:42:06 +08:00
chenfeiyu 57d820f055 add support for channel last in batch_spec, and Conv1dBatchNorm 2020-10-30 15:13:57 +08:00
chenfeiyu 36cc543348 minor fixes to TransformerTTS 2020-10-28 11:05:47 +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 2a764d9a10 add opencc, g2p_en, g2pm into requirements 2020-10-20 16:08:45 +08:00
iclementine 580655f33f add phonetics & vocab & punctuation 2020-10-20 16:06:11 +08:00
iclementine c1e0aecdde 1. import models into parakeet.models;
2. add predict for TransformerTTS and test its io.
2020-10-16 13:51:56 +08:00
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 5270774bb0 tested io for TransformerTTS 2020-10-15 22:48:09 +08:00
iclementine 40457227e6 move Conv1dBatchNorm to conv.py 2020-10-14 10:05:26 +08:00
iclementine f9087ea9a2 add masking functions 2020-10-13 15:53:18 +08:00
iclementine a8192c79cc WIP: refactor 2020-10-10 15:51:54 +08:00
Li Fuchen 1db01ccc90
Merge pull request #35 from ShenYuhan/fix_bug
fix bugs of vdl
2020-08-25 17:41:39 +08:00
Li Fuchen 3879b5ecb9
Merge pull request #22 from lfchener/fix
modified help massage of max_len in TransformerTTS synthesis
2020-08-25 17:38:47 +08:00
ShenYuhan bb5f445212 fix bugs 2020-08-20 13:27:42 +08:00
Li Fuchen ce8fad5412
Merge pull request #31 from ShenYuhan/add_vdl
add visualdl for parakeet
2020-08-20 11:39:17 +08:00
ShenYuhan c140e9cf5b update visualdl version 2020-08-18 20:37:55 +08:00
ShenYuhan 2933eb7e57 replace add_scalar to add_scalars 2020-08-14 17:48:24 +08:00
liuyibing01 b604d1c7dd Merge branch 'develop' into 'master'
examples/deepvoice3 minor fixes

See merge request !73
2020-08-12 16:29:29 +08:00
chenfeiyu 3717ac1342 add max_iteration into configuration, fix np.pad for lower versions of numpy 2020-08-11 09:22:08 +00:00
ShenYuhan bf6d9ef06f add visualdl for parakeet 2020-08-07 16:28:21 +08:00
liuyibing01 610181d4c0 Merge branch 'develop' into 'master'
dv3 miscellaneous enhancements.

See merge request !67
2020-07-29 12:21:49 +08:00
chenfeiyu ddf1c4f7a7 1. fix initializers;
2. use simple random sampler;
3. clean code for gradient clipper.
2020-07-29 11:54:47 +08:00
Yibing Liu 47915461fc Adapt waveflow to internal dataset 2020-07-28 17:34:38 +00:00
liuyibing01 e58e927c5e Merge branch 'dv3_reload' into 'master'
remove weigth norm when synthesizing to make inference fatser

See merge request !66
2020-07-17 19:28:01 +08:00
chenfeiyu de6e15339f remove weigth norm when synthesizing to make inference fatser 2020-07-17 17:56:23 +08:00
Yibing Liu 45f6e55911 Merge branch 'master' of upstream 2020-07-16 13:39:53 +08:00
Yibing Liu ef83782e44 Release waveflow res. channel 96 2020-07-16 13:39:30 +08:00
liuyibing01 2131d79723 Merge branch 'develop' into 'master'
add model architecture

See merge request !65
2020-07-14 15:10:15 +08:00
chenfeiyu 60506d436a add model architecture 2020-07-14 15:05:26 +08:00