How to use to find yelling and laughter in a longer video?
#8
by
rj14694
- opened
I have been looking at this model for quite some time, but I'm not sure how I could use it to label an hour or 1.5 hour long audio to find specific tags like laughter, screaming, yelling ect.
How would I go about this?
Do I just need to segment the audio array that I input?