234 Commits

Author	SHA1	Message	Date
root	0e8881114b	efficient GMM attneiton with native broadcasting	2020-01-10 13:45:09 +01:00
root	f2b6d00c45	grave attention config update:	2020-01-07 18:47:02 +01:00
geneing	748cbbc403	Change to GMMv2b	2020-01-05 18:34:01 -08:00
geneing	34e0291ba7	Change to GMMv2b	2020-01-05 18:32:49 -08:00
geneing	20b4211af5	Change to GMMv2b	2020-01-05 18:32:35 -08:00
Eren Golge	79cca4ac80	more loss tests	2019-11-15 14:30:28 +01:00
Eren Golge	cd06a4c1e5	linter fix	2019-11-12 13:51:22 +01:00
Eren Golge	df1b8b3ec7	linter and test updates for speaker_encoder, gmm_Attention	2019-11-12 12:42:42 +01:00
Eren Golge	1401a0db6b	update GMM attention calp max min	2019-11-12 11:20:53 +01:00
Eren Golge	6f3dd1b6ae	chnage gmm activations	2019-11-12 11:20:53 +01:00
Eren Golge	015f7780f4	Decoder shape comments for Tacotron2, decoupled grad clip for stopnet and the rest of the network. Some variable renaming and bug fix for alignment score logging	2019-11-12 11:20:53 +01:00
Eren Golge	2966e3f2d1	use ReLU for GMM	2019-11-12 11:20:53 +01:00
Eren Golge	b904bc02d6	config update and initial bias for graves attention	2019-11-12 11:19:57 +01:00
Eren Golge	926a4d36ce	change tanh layer size for graves attention	2019-11-12 11:19:16 +01:00
Eren Golge	fb34c7b272	config and bug fix	2019-11-12 11:19:16 +01:00
Eren Golge	695bf1a1f6	bug fix for illegal memory reach	2019-11-12 11:19:16 +01:00
Eren Golge	b9e0faca98	config update and bug fixes	2019-11-12 11:19:16 +01:00
Eren Golge	adf9ebd629	Graves attention and setting attn type by config.json	2019-11-12 11:18:57 +01:00
Eren Golge	84d81b6579	graves attention [WIP]	2019-11-12 11:17:35 +01:00
Eren Golge	ec579d02a1	bug fix argparser	2019-10-31 15:13:39 +01:00
Eren Golge	60b6ec18fe	bug fix for synthesis.py	2019-10-29 17:38:59 +01:00
Eren Golge	002991ca15	bug fixes, linter update and test updates	2019-10-29 14:28:49 +01:00
Eren Golge	89ef71ead8	bug fix tacotron2, decoder return order fixed	2019-10-29 13:32:20 +01:00
Eren Golge	5a56a2c096	bug fixes for forward backward training and load_data for parsing data_loader	2019-10-29 02:58:42 +01:00
Eren Golge	e83a4b07d2	commention model outputs for tacotron, align outputs shapes of tacotron and tracotron2, merge bidirectional decoder	2019-10-28 14:51:19 +01:00
Eren Golge	9d5a5b0764	linter	2019-10-24 14:34:31 +02:00
Eren Golge	ea32f2368d	linter fix	2019-10-24 14:11:07 +02:00
Eren Golge	77f5fd0584	compute and config update with new attention entropy loss	2019-10-15 15:05:42 +02:00
Eren Golge	53ec066733	replace zeros() with a better alternative	2019-10-12 18:34:12 +02:00
Eren Golge	98af061d2e	formatting, merge GST model with Tacotron	2019-09-24 16:18:48 +02:00
Eren Golge	e8d29613f1	fix stop condition	2019-09-24 15:38:28 +02:00
Eren Golge	9a2bd7f9af	fix for 2 dim memory tensor	2019-09-23 10:25:51 +02:00
Eren Golge	e085c4757d	bug fix	2019-09-23 10:25:51 +02:00
Eren Golge	8d3775a7d6	Update tacotron2 for gradual training and chnage the indexing of prenet nputs to oick the last frame	2019-09-23 10:25:51 +02:00
Eren Golge	a1322530df	integrade concatinative speker embedding to tacotron	2019-09-12 10:39:15 +02:00
Reuben Morais	3c5aeb5e22	Fix installation by using an explicit symlink	2019-08-29 11:49:53 +02:00
Eren Golge	72ad58d893	change the bitwise for masking and small fixes	2019-08-19 16:24:28 +02:00
Eren Golge	c637aa04a2	pylint	2019-08-16 15:49:12 +02:00
Eren Golge	5629292bde	bug fixes	2019-08-16 15:08:04 +02:00
Eren Golge	8fde0ac00e	pylint	2019-08-16 14:23:26 +02:00
Eren Golge	b22c7d4a29	Merge branch 'dev-gradual-queue' into dev	2019-08-16 13:20:17 +02:00
Eren Golge	64f2b95c31	update regarding torch 1.2	2019-08-13 12:14:34 +02:00
Thomas Werkmeister	ab42396fbf	undo loc attn after fwd attn	2019-07-25 13:04:41 +02:00
Thomas Werkmeister	f3dac0aa84	updating location attn after calculating fwd attention	2019-07-24 11:49:07 +02:00
Thomas Werkmeister	40f56f9b00	simplified code for fwd attn	2019-07-24 11:47:06 +02:00
Thomas Werkmeister	a6118564d5	renamed query_rnn back to attention_rnn	2019-07-24 11:46:34 +02:00
Thomas Werkmeister	fb7c5b1996	unused instance vars	2019-07-23 20:02:31 +02:00
Thomas Werkmeister	82db35530f	unused var	2019-07-23 19:33:56 +02:00
Thomas Werkmeister	98edb7a4f8	renamed attention_rnn to query_rnn	2019-07-23 18:38:09 +02:00
Eren Golge	2bbb3f7a40	don't use sigmoid output for tacotron, fix bug for memory queue handling, remove maxout	2019-07-22 15:09:05 +02:00