Including sound classification for SDH subtitles? #252
kuroderuta
started this conversation in
Ideas
Replies: 1 comment
-
|
Such feature doesn't exist. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
SDH stands for subtitles for the deaf and hard of hearing. These subtitles assume the end user cannot hear the dialogue and include important non-dialogue information such as expressions, sound effects or music.
This is both a question if such feature exists and a request if it doesn't. I noticed that sometime Whisper will hallucinate an output like [laugher] but its not consistent and I haven't found the settings to force those. There are also VADs like YAMNet which could perhaps help fill the gap.
Beta Was this translation helpful? Give feedback.
All reactions