You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have built whisper on a RISCV platform that supports RVV1.0 as well as some NPU things. I see that there is code in GGML that can take advantage of this through compiler intrinsics provided the right modules are selected at link time and the correct conditional compilations are taken. How can I check that these are in fact being used instead of some generic C code? The reason I ask is that when I run the JFK sample through whisper-cli it is spending 89% of its time in the 'encode' phase and taking nearly 3x the duration of the input audio.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
I have built whisper on a RISCV platform that supports RVV1.0 as well as some NPU things. I see that there is code in GGML that can take advantage of this through compiler intrinsics provided the right modules are selected at link time and the correct conditional compilations are taken. How can I check that these are in fact being used instead of some generic C code? The reason I ask is that when I run the JFK sample through
whisper-cliit is spending 89% of its time in the 'encode' phase and taking nearly 3x the duration of the input audio.Beta Was this translation helpful? Give feedback.
All reactions