deviandice/tortoise-tts
1
0
Fork 0
forked from mrq/tortoise-tts
Code Issues Pull Requests Packages Projects Releases Wiki Activity
(QoL improvements for) a multi-voice TTS system trained with an emphasis on quality
296 Commits 2 Branches 0 Tags 556 KiB
Python 99.9%
e650800447
Go to file
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
config
convert modified conversion scripts to not give a shit about bitrate and formats since torchaudio.load handles all of that anyways, and it all gets resampled anyways 2023-02-15 04:44:14 +00:00
scripts
tortoise Update 'tortoise/utils/device.py' 2023-03-07 14:05:27 +00:00
.gitignore added shell scripts for linux, wrapped sorted() for voice list, I guess 2023-02-06 21:54:31 -06:00
CITATION.cff
LICENSE
MANIFEST.in
README.md you should have migrated by now, if anything breaks it's on (You) 2023-03-05 14:03:18 +00:00
requirements_legacy.txt pip-ifying things 2023-02-16 19:48:06 +00:00
requirements.txt pip-ifying things 2023-02-16 19:48:06 +00:00
setup.py added option to specify autoregressive model at tts generation time (for a spicy feature later) 2023-03-06 20:31:19 +00:00

README.md

(QoL improvements for) TorToiSe

This repo is for my modifications to neonbjb/tortoise-tts. If you need the original README, refer to the original repo.

> w-where'd everything go?

Please migrate to mrq/ai-voice-cloning, as that repo is the more cohesive package for voice cloning.