Commit Graph

112 Commits

Author SHA1 Message Date
chenfeiyu a4a0bd8c98 add last bn for the decoder postnet, switch back to weighted mean 2020-12-05 14:00:08 +08:00
chenfeiyu c57e8e7350 fix transformer_tts' stop condition 2020-12-04 02:11:02 +08:00
chenfeiyu e87bfb7d05 hide fastspeech, deepvoice3, clarinet temporarily till they are updated 2020-12-03 18:54:17 +08:00
chenfeiyu 4df5ad42f6 remove the last layer from decoder prenet 2020-12-03 15:55:07 +08:00
chenfeiyu 810f979dba siwtch to keras style sample_weight in losses 2020-12-03 15:37:43 +08:00
chenfeiyu 404add2caa temporary fix for memory leak 2020-12-03 14:51:25 +08:00
chenfeiyu 9cb5c03069 transformer_tts, miscellaneous fixes 2020-12-01 18:13:30 +08:00
iclementine a01200e437 add an cli for cloning examples 2020-11-19 18:08:11 +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 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 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 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
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
chenfeiyu 282c36c2c1 dv3 reloaded, back to the origin 2020-07-10 20:22:43 +08:00
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
liuyibing01 c170b5a282 Merge branch 'commit' into 'master'
fix some bugs of transformer_tts and fastspeech.

See merge request !58
2020-06-12 16:55:39 +08:00
lifuchen 681d34b953 fix some bugs of transformer_tts and fastspeech. 2020-06-12 08:54:32 +00:00
Yibing Liu 33ed693ccf Upgrade waveflow api to 1.8.2 2020-06-12 08:45:55 +00:00
Yibing Liu 9b8fd9f93d Upgrade waveflow to 1.8.0 2020-05-22 07:16:45 +00:00
liuyibing01 8716a1843c Merge branch 'refactor' into 'master'
refactor for deep voice 3, update wavenet and clarinet to use enable_dygraph

See merge request !53
2020-05-22 14:28:57 +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
lifuchen d1ba42ea68 modified fastspeech to make sure it works on paddle 1.8 2020-05-08 03:58:45 +00:00
lifuchen 55fa94f15d Merge branch 'master' of upstream. 2020-05-08 03:47:40 +00:00
chenfeiyu e0ba85f6b5 update for wavenet and clarinet 2020-05-08 03:33:27 +00:00
lifuchen 46e254d1f8 modified transformer_tts to make sure it works on paddle 1.8 2020-05-07 02:23:50 +00:00
chenfeiyu ff1d66ea94 update for deepvoice3, fix weight norm 2020-05-06 08:36:43 +00:00
lifuchen c1b837dc17 completed fastspeech and modified save/load 2020-04-09 12:06:04 +00:00
lifuchen f312b2f05c Merge branch 'master' of upstream 2020-04-07 09:34:39 +00:00
lifuchen ad4b248af8 fix some bug of mask in fastspeech 2020-04-07 09:34:27 +00:00
liuyibing01 618eb31ab4 Adapt the change in save & load 2020-03-26 09:27:22 +00:00
liuyibing01 fccbf6d797 Update README 2020-03-26 06:45:22 +00:00
liuyibing01 64790853e5 Unify save & load interfaces 2020-03-22 08:05:05 +00:00
liuyibing01 be70b41fd1 Merge branch 'master' into 'master'
fixes for wavenet and modules

See merge request !47
2020-03-22 11:44:42 +08:00
chenfeiyu 67613951d5 minor fixes for wavent and modules 2020-03-21 11:52:15 +00:00
lifuchen 75d464221c modified the process of generating masks to speed up batching 2020-03-20 09:37:49 +00:00
liuyibing01 f618b21765 Add a comment before layer pad2d 2020-03-13 06:05:57 +00:00
liuyibing01 bfbc5e2046 Upgrade to paddle 1.7.1 2020-03-12 14:20:46 +00:00