mrq/tortoise-tts
4
6
Fork 15
Code Issues 9 Pull Requests 1 Packages Projects Releases Wiki Activity

reverting additional auto-suggested batch sizes, per mrq/ai-voice-cloning#87 proving it in fact, is not a good idea

Browse Source
This commit is contained in:
mrq 2023-03-07 19:38:02 +00:00
parent cc36c0997c
commit 3dd5cad324
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tortoise/utils/device.py
View File

@ -61,10 +61,8 @@ def get_device_batch_size():
available = psutil.virtual_memory()[4] available = psutil.virtual_memory()[4]
vram = available / (1024 ** 3) vram = available / (1024 ** 3)
if vram > 18: # I'll need to rework this better
return 32 # simply adding more tiers clearly is not a good way to go about it
if vram > 16:
return 24
if vram > 14: if vram > 14:
return 16 return 16
elif vram > 10: elif vram > 10: