* Fix voice extractor (#483)

* changes

* changes

* Minor cleanup

* Use 48000 everywhere

* Fix test

* Balance between processing and VRAM

* Warmup the read_static_voice() cache

* Warmup the read_static_voice() cache

* Simplify replace_audio to prevent FFmpeg 7 infite loop

* Fix potential exception in conditional download

* Add more deoldify models

* Rename eye-glasses to glasses, Prepare release 2.5.1

---------

Co-authored-by: Harisreedhar <46858047+harisreedhar@users.noreply.github.com>
This commit is contained in:
Henry Ruhs
2024-04-13 11:27:55 +02:00
committed by GitHub
parent f77c463531
commit 092dfbb796
13 changed files with 44 additions and 21 deletions

View File

@@ -37,7 +37,7 @@ FACE_MASK_REGIONS : Dict[FaceMaskRegion, int] =\
'right-eyebrow': 3,
'left-eye': 4,
'right-eye': 5,
'eye-glasses': 6,
'glasses': 6,
'nose': 10,
'mouth': 11,
'upper-lip': 12,