51 Commits

Author	SHA1	Message	Date
Daniel Povey	633213424d	Rework of initialization	2022-03-16 12:42:59 +08:00
Daniel Povey	261d7602a7	Draft of 0mean changes..	2022-03-15 23:46:53 +08:00
Daniel Povey	fc873cc50d	Make epsilon in BasicNorm learnable, optionally.	2022-03-15 17:00:17 +08:00
Daniel Povey	1962fe298b	Add deriv-balancer at output of embedding.	2022-03-15 14:35:15 +08:00
Daniel Povey	86e5dcba11	Remove max-positive constraint in deriv-balancing; add second DerivBalancer in conv module.	2022-03-15 13:10:35 +08:00
Daniel Povey	a23010fc10	Add warmup mode	2022-03-14 23:04:51 +08:00
Daniel Povey	8d17a05dd2	Reduce constraints from deriv-balancer in ConvModule.	2022-03-14 19:23:33 +08:00
Daniel Povey	437e8b2083	Reduce max-abs limit from 1000 to 100; introduce 2 DerivBalancer modules in conv layer.	2022-03-13 23:31:08 +08:00
Daniel Povey	f351777e9c	Remove ExpScale in feedforward layes.	2022-03-13 17:29:39 +08:00
Daniel Povey	97c0bb82d3	Change dir name	2022-03-13 13:19:20 +08:00
Daniel Povey	e6a501d3c8	Add max-abs-value constraint in DerivBalancer	2022-03-13 11:52:13 +08:00
Daniel Povey	6042c96db2	Use learnable scales for joiner and decoder	2022-03-12 20:54:46 +08:00
Daniel Povey	a392cb9fbc	Reduce initial scaling of modules	2022-03-12 16:53:03 +08:00
Daniel Povey	d906bc2a4f	Change dir name	2022-03-12 15:38:39 +08:00
Daniel Povey	76a2b9d362	Add learnable post-scale for mha	2022-03-12 11:19:49 +08:00
Daniel Povey	cc558faf26	Fix scale from 0.5 to 2.0 as I really intended..	2022-03-11 19:11:50 +08:00
Daniel Povey	98156711ef	Introduce in_scale=0.5 for SwishExpScale	2022-03-11 19:07:34 +08:00
Daniel Povey	5eafccb369	Change how scales are applied; fix residual bug	2022-03-11 17:46:33 +08:00
Daniel Povey	bec33e6855	init 1st conv module to smaller variance	2022-03-11 16:37:17 +08:00
Daniel Povey	ab9a17413a	Scale up pos_bias_u and pos_bias_v before use.	2022-03-11 14:37:52 +08:00
Daniel Povey	e3e14cf7a4	Change min-abs threshold from 0.2 to 0.5	2022-03-11 14:16:33 +08:00
Daniel Povey	bfce5f63e4	Fix dirname	2022-03-10 23:49:09 +08:00
Daniel Povey	76560f255c	Add min-abs-value 0.2	2022-03-10 23:48:46 +08:00
Daniel Povey	2fa9c636a4	use nonzero threshold in DerivBalancer	2022-03-10 23:24:55 +08:00
Daniel Povey	425e274c82	Replace norm in ConvolutionModule with a scaling factor.	2022-03-10 16:01:53 +08:00
Daniel Povey	87b843f023	Change exp dir	2022-03-10 14:44:55 +08:00
Daniel Povey	e2ace9d545	Replace norm on input layer with scale of 0.1.	2022-03-07 11:24:04 +08:00
Daniel Povey	a37d98463a	Restore ConvolutionModule to state before changes; change all Swish,Swish(Swish) to SwishOffset.	2022-03-06 11:55:02 +08:00
Daniel Povey	8a8b81cd18	Replace relu with swish-squared.	2022-03-05 22:21:42 +08:00
Daniel Povey	5f2c0a09b7	Convert swish nonlinearities to ReLU	2022-03-05 16:28:24 +08:00
Daniel Povey	0cd14ae739	Fix exp dir	2022-03-05 12:17:09 +08:00
Daniel Povey	6252282fd0	Add deriv-balancing code	2022-03-04 20:19:11 +08:00
Daniel Povey	9cc5999829	Fix duplicate Swish; replace norm+swish with swish+exp-scale in convolution module	2022-03-04 15:50:51 +08:00
Daniel Povey	7e88999641	Increase scale from 20 to 50.	2022-03-04 14:31:29 +08:00
Daniel Povey	3207bd98a9	Increase scale on Scale from 4 to 20	2022-03-04 13:16:40 +08:00
Daniel Povey	23b3aa233c	Double learning rate of exp-scale units	2022-03-04 00:42:37 +08:00
Daniel Povey	5c177fc52b	pelu_base->expscale, add 2xExpScale in subsampling, and in feedforward units.	2022-03-03 23:52:03 +08:00
Daniel Povey	3fb559d2f0	Add baseline for the PeLU expt, keeping only the small normalization-related changes.	2022-03-02 18:27:08 +08:00
Daniel Povey	9d1b4ae046	Add pelu to this good-performing setup..	2022-03-02 16:33:27 +08:00
Daniel Povey	c1063def95	First version of rand-combine iterated-training-like idea.	2022-02-27 17:34:58 +08:00
Daniel Povey	581786a6d3	Adding diagnostics code...	2022-02-27 13:44:43 +08:00
Daniel Povey	2af1b3af98	Remove ReLU in attention	2022-02-14 19:39:19 +08:00
Daniel Povey	d187ad8b73	Change max_frames from 0.2 to 0.15	2022-02-11 16:24:17 +08:00
Daniel Povey	4cd2c02fff	Fix num_time_masks code; revert 0.8 to 0.9	2022-02-10 15:53:11 +08:00
Daniel Povey	c170c53006	Change p=0.9 to p=0.8 in SpecAug	2022-02-10 14:59:14 +08:00
Daniel Povey	8aa50df4f0	Change p=0.5->0.9, mask_fraction 0.3->0.2	2022-02-09 22:52:53 +08:00
Daniel Povey	beaf5bfbab	Merge specaug change from Mingshuang.	2022-02-08 19:42:23 +08:00
Wei Kang	5ae80dfca7	Minor fixes (#193)	2022-01-27 18:01:17 +08:00
Fangjun Kuang	14c93add50	Remove batchnorm, weight decay, and SOS from transducer conformer encoder (#155) ... * Remove batchnorm, weight decay, and SOS. * Make --context-size configurable. * Update results.	2021-12-27 16:01:10 +08:00
Fangjun Kuang	fb6a57e9e0	Increase the size of the context in the RNN-T decoder. (#153)	2021-12-23 07:55:02 +08:00