Feature request - [Print "Speech" while talking] #548
Answered
by
snakers4
RoboEvangelist
asked this question in
Q&A
-
|
Is there a way to allow silero to print "possible speech detected" every N milliseconds? This is as opposed to waiting for a recording to finish and then printing "possible speech detected" at the end |
Beta Was this translation helpful? Give feedback.
Answered by
snakers4
Oct 6, 2024
Replies: 1 comment
-
|
The VAD outputs probability each ~30ms. So you are free to do any post-processing / aggregation you would like. A good start is to modify the logic behind the get speech timestamps function. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
snakers4
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
The VAD outputs probability each ~30ms. So you are free to do any post-processing / aggregation you would like.
A good start is to modify the logic behind the get speech timestamps function.