deviandice e650800447 Update 'tortoise/utils/device.py' ... Noticed that the autoregressive batch size was being set off of VRAM size. Adjusted to scale for the VRAM capacity of 90 series GPUs. In this case, 16 -> 32 batches. Using the standard pre-set with ChungusVGAN, I went from 16 steps to 8. Over an average of 3 runs, I achieved an average of 294 seconds with 16 batches, to 234 seconds with 32. Can't complain at a 1.2x speed increase with functionally 2 lines of code. Can't complain. I restarted tortoise each run, and executing ```torch.cuda.empty_cache()``` just before loading the autoregressive model to clean the memory cache each time.		2023-03-07 14:05:27 +00:00
..
data	Add chapter 1 of GoT for read.py demos	2022-05-17 11:21:57 -06:00
models	added BigVGAN in place of default vocoder (credit to https://github.com/deviandice/tortoise-tts-BigVGAN)	2023-03-03 06:30:58 +00:00
utils	Update 'tortoise/utils/device.py'	2023-03-07 14:05:27 +00:00
__init__.py	Move everything into the tortoise/ subdirectory	2022-05-01 16:24:24 -06:00
api.py	do not reload AR/vocoder if already loaded	2023-03-07 04:33:49 +00:00
do_tts.py	QoL fixes	2023-02-02 21:13:28 +00:00
eval.py	add eval script for testing	2022-05-12 20:15:22 -06:00
get_conditioning_latents.py	fixed up the computing conditional latents	2023-02-06 03:44:34 +00:00
is_this_from_tortoise.py	misc fixes	2022-05-02 18:00:57 -06:00
read.py	Fixed silly lack of EOF blank line, indentation	2022-06-06 15:13:29 -05:00