-
Notifications
You must be signed in to change notification settings - Fork 4.6k
-
Hey everyone! I have a question about the karaoke-style speech recognition. Do you think it will work in real time? It seems it's really good with recorded audio but will it work in real-time speech? Any feedback or answers appreciated.
Thank you in advance!
Beta Was this translation helpful? Give feedback.
All reactions
Replies: 2 comments
-
Whisper is not real-time, nor is it likely to ever be real-time. It works by processing audio 30 seconds at a time, and that processing, even when GPU-accelerated, can take a significant fraction of a second, or even several seconds.
Beta Was this translation helpful? Give feedback.
All reactions
0 replies
-
Thanks
... On Wed, 5 Jun 2024, 00:05 ulatekh, ***@***.***> wrote:
Whisper is not real-time, nor is it likely to ever be real-time. It works
by processing audio 30 seconds at a time, and that processing, even when
GPU-accelerated, can take a significant fraction of a second, or even
several seconds.
—
Reply to this email directly, view it on GitHub
<#1206 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AUDBSE67MG25ECR2KBXS4RTZFYT2ZAVCNFSM6AAAAAA36EDHT6VHI2DSMVQWIX3LMV43SRDJONRXK43TNFXW4Q3PNVWWK3TUHM4TMNRZHA2TM>
.
You are receiving this because you authored the thread.Message ID:
***@***.***>
Beta Was this translation helpful? Give feedback.
All reactions
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment