13 commits

Author	SHA1	Message	Date
NourEldin Osama	4d4a423971	Update autoregressive.py ... Fix AttributeError: module 'torch.backends.cuda' has no attribute 'is_available'	2023-08-11 20:08:19 +03:00
manmay nakhashi	4ad73a143d	check cuda in deepspeed init	2023-08-11 21:02:08 +05:30
Jerry-Master	b4988c24b3	Added MPS support for do_tts	2023-08-06 17:41:30 +02:00
manmay-nakhashi	180d65d0fb	add parallelize back as it was already there	2023-07-16 15:42:53 +05:30
manmay-nakhashi	45462c6cf1	pass half from TexttoSpeech args	2023-07-16 14:25:42 +05:30
manmay-nakhashi	19f5250454	add half because kv_cache increases memory footprint	2023-07-16 00:49:17 +05:30
manmay-nakhashi	a88534adb2	added kv_cache	2023-07-15 23:00:19 +05:30
manmay-nakhashi	82724cca54	import deepspeed only if use_deepspeed is True	2023-07-10 07:47:46 +05:30
manmay-nakhashi	5a9707d93c	added deepspeed inference	2023-07-09 18:40:10 +05:30
James Betker	cdf44d7506	more fixes	2022-05-02 16:44:47 -06:00
James Betker	39ec1b0db5	Support totally random voices (and make fixes to previous changes)	2022-05-02 15:40:03 -06:00
James Betker	0ffc191408	Add support for extracting and feeding conditioning latents directly into the model ... - Adds a new script and API endpoints for doing this - Reworks autoregressive and diffusion models so that the conditioning is computed separately (which will actually provide a mild performance boost) - Updates README This is untested. Need to do the following manual tests (and someday write unit tests for this behemoth before it becomes a problem..) 1) Does get_conditioning_latents.py work? 2) Can I feed those latents back into the model by creating a new voice? 3) Can I still mix and match voices (both with conditioning latents and normal voices) with read.py?	2022-05-01 17:25:18 -06:00
James Betker	f7c8decfdb	Move everything into the tortoise/ subdirectory ... For eventual packaging.	2022-05-01 16:24:24 -06:00

Renamed from models/autoregressive.py (Browse further)