News for hackers. Stuff that matters.
Re:GPUs for Deep Learning in 2023 – An In-depth Analysis by fxtentacle on Thursday January 19, 2023 @09:21AM (#34440526)
That's how cloud speech recognition is usually deployed. OpenAI whisper is faster than realtime on regular desktop CPUs, which I guess is good enough.

And for a datacenter, a few $100 AMD CPUs will beat a single $20k NVIDIA A100 at throughput per dollar.

There are no comments on this comment yet.