RunTime too long! #2164
HduHestin
started this conversation in
Show and tell
Replies: 1 comment
-
I believe it's because when you use the "cpu" parameter, you're putting the entire load of the computation on the cpu rather than the gpu. |
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
Uh oh!
There was an error while loading. Please reload this page.
-
i use model = whisper.load_model("base","cpu"), and other code is same with whisper examples,

5 seconds audio use 93.8684 seconds
but when i use model = whisper.load_model("base")
same 5 second audio use 0.9159 seconds
i want to know whether the difference is normal?
Beta Was this translation helpful? Give feedback.
All reactions