Algorithm info: This way the source material shouldn't be affected by the current bug(?) using 2_HP_UVR.
Processing 2_HP_UVR again, with 0.005s added to the original MVsep dataset prior
(since that's the amount that would get cut off during the process).
Checking the output of the ones it finished, and no cut off whatsoever?!
So I stopped the process, and tried on the original dataset (untouched) again.
And... it does cut off 0.005s(!)
I have no idea what's causing this (roundings? but we're dealing with sample amount, not ms rly),
but I'd like to ask @Anjok to take a look asap.
Submitted by Bas Curtiz
Version: UVR v5.5.0/Patch_12_22_22_23_44/Win
Advanced VR:
Window Size: 272
Aggression: 10
Crop size: 256
Batch Size: 4
Enable TTA: On
Post-Process: Off
High-End Process: On
Based on SYRKOV's suggestion at Audio Separation Discord:
"who can say, if there a difference between 2_HP-UVR and 7_HP2-UVR?"
Time Elapsed: 01:29:20
Date added: 2022-12-27 |
