testadmin
/
Parakeet
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
358 Commits 8 Branches 7 Tags 7 MiB
Commit Graph

358 Commits

Author SHA1 Message Date
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
Yibing Liu 4938a13866 Correct table format 2020-07-14 14:25:15 +08:00
liuyibing01 13a9fe878e Merge branch 'dv3_reload' into 'master' 
add griffin lim as an alternative vocoder

See merge request !64
 2020-07-14 14:02:47 +08:00
chenfeiyu 8a5f9d75b6 update README and command line help msg 2020-07-14 11:33:15 +08:00
lfchener 1eb9a273e9 modified help massage of max_len in TransformerTTS synthesis. 2020-07-13 15:36:21 +08:00
chenfeiyu 7938a5f6a4 add griffin lim as an alternative vocoder 2020-07-13 15:19:52 +08:00
Yibing Liu 462491ab45 Remove dv3 ckpt temporarily 2020-07-11 10:07:06 +08:00
liuyibing01 16c2fd3044 Merge branch 'dv3_reload' into 'master' 
dv3 reloaded, back to the origin

See merge request !63
 2020-07-11 09:55:01 +08:00
chenfeiyu 282c36c2c1 dv3 reloaded, back to the origin 2020-07-10 20:22:43 +08:00
Yibing Liu 24eb14a718 Update readme 2020-06-24 12:16:27 +08:00
Yibing Liu 669a65a1e3 Update checkpoints and audio samples for transformer_tts & fastspeech 2020-06-24 11:59:37 +08:00
liuyibing01 563d3bae74 Merge branch 'commit' into 'master' 
modified data preprocessing and synthesis of transformer_tts and fastspeech

See merge request !62
 2020-06-24 11:31:35 +08:00
lifuchen a333e64f79 modified README of transformer_tts and fastspeech 2020-06-24 03:27:45 +00:00
lifuchen 5b804b70e6 modified some config name and default path. 2020-06-24 02:52:22 +00:00
lifuchen abdc0a729f Merge branch 'master' of upstream into commit 2020-06-23 12:53:36 +00:00
lifuchen aaae100854 modified data preprocessing and synthesis of transformer_tts and fastspeech 2020-06-23 12:52:58 +00:00
lifuchen 14235cd114 modified synthesis of transformer_tts & fastspeech 2020-06-19 03:46:10 +00:00
liuyibing01 c68c6a22af Merge branch 'fix' into 'master' 
pin llvmlite version to 0.31.0

See merge request !61
 2020-06-13 10:30:40 +08:00
chenfeiyu 91b1a3af5b pin llvmlite version to 0.31.0 2020-06-12 12:24:25 +00:00