17 Commits

Author	SHA1	Message	Date
mrq	6ca347e1e1	literally had a urethra moment before going to bed with a way to implement cse/nse tasks	2023-08-19 01:16:46 -05:00
mrq	8f42c578c9	setting up for allowing training for a partial amount of the speechx tasks (do NOT try this at home yet without a proper model, as performance is predecated on having a solid base vall-e model for the tasks	2023-08-19 00:16:08 -05:00
mrq	ae9d38aa31	forgot to have it pull from specified noise to the hdf5 dataset	2023-08-18 23:57:07 -05:00
mrq	77292c42f9	tested the training preparation for tasks ns, sr, and tse (I don't expect it to go well with only 2 RVQ bins)	2023-08-18 23:55:40 -05:00
mrq	bbb0563b3d	pseudocode polyfill stub some other flavor of working on adding the tasks	2023-08-18 22:22:13 -05:00
mrq	2a71486cb6	preparing for SpeechX extensions	2023-08-18 20:58:07 -05:00
mrq	ced31fd9b7	removed the sampler as it's very misleading	2023-08-18 14:47:48 -05:00
mrq	8e7f900210	forgot the =	2023-08-17 19:07:59 -05:00
mrq	3ff7cf8341	maybe fix evaluation dataset not being capped to cfg.evaluation.size	2023-08-17 18:56:37 -05:00
mrq	ee58db746f	actually make the evaluation dataset shuffled for sample_type=speaker	2023-08-17 15:04:45 -05:00
mrq	18403a3523	maybe fixes eval dataloader not shuffling under distributed	2023-08-17 13:41:53 -05:00
mrq	b5f247aa11	just nuked about 9 hours of progress because I didn't make sure it pruned only on the global leader	2023-08-16 23:37:52 -05:00
mrq	44c08d828e	added sample_type that samples from speakers to truly balance an epoch by speakers rather than the entire dataset and a sampler that tries to balance by speakers	2023-08-16 19:39:21 -05:00
mrq	277c759ab1	fixed issue with non-distributed training, oops	2023-08-14 21:42:35 -05:00
mrq	5fa86182b5	oops	2023-08-14 10:50:40 -05:00
mrq	d7deaf6def	distributed training works now (hopefully)	2023-08-13 22:07:45 -05:00
mrq	bf8cedc9dd	Rewrite init	2023-08-02 21:53:35 +00:00