Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
justinclift
on Feb 21, 2024
|
parent
|
context
|
favorite
| on:
The killer app of Gemini Pro 1.5 is using video as...
As it says the audio is stripped/removed from video before processing, wonder how well it'd do if asked to transcribe by lip reading?
simonw
on Feb 21, 2024
[–]
It looks like it actually only considers one frame for every second of video, so that certainly wouldn't work.
justinclift
on Feb 22, 2024
|
parent
[–]
Yeah. If that interval isn't able to be adjusted then you're likely right. Oh well. ;)
Join us for
AI Startup School
this June 16-17 in San Francisco!
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
