17x realtime on a 3090
I did some basic tests on CPU, the "small" Whisper model is in the ballpark of 0.5x realtime, which is probably not great for interactive use.
My models in Talon run closer to 100x realtime on CPU.
I did some basic tests on CPU, the "small" Whisper model is in the ballpark of 0.5x realtime, which is probably not great for interactive use.
My models in Talon run closer to 100x realtime on CPU.
Brute forcing the model with just traditional CPU instructions is fine, but… obviously going to be pretty slow.
I have no experience on the accuracy of Talon, but I’ve heard that most open source models are basically overfit to the test datasets… so their posted accuracy is often misleading. If Whisper is substantially better in the real world, that’s the important thing, but I have no idea if that’s the case.
tiny.en: ~18 sec/sec
base.en: ~14 sec/sec
small.en: ~6 sec sec/sec
medium.en: ~2.2 sec/sec
large: ~1.0 sec/sec (fairly wide variance when ramping up as this is slow to process individual clips)
EDIT: for what it's worth, Nvidia rated the A2 at 18 TFLOPS of FP16, and Apple rates the current A16 Neural Engine at 17 TFLOPS of FP16. I'm sure it's not an "apples to apples" comparison.
Sure, the Whisper Tiny model is probably going to be fast enough, but from my preliminary results I'm not sure it will be any better than other models that are much much faster at this power class.
Whisper Large looks pretty cool, but it seems much harder to run in any meaningful realtime fashion. It's likely pretty useful for batch transcription though.
Even if you hit a realtime factor of 1x, the model can leverage up to 30 seconds of future audio context. So at 1x, if you speak for 10 seconds, you'll potentially need to wait another 10 seconds to use the result. This kind of latency is generally unsatisfying.
----
With Siri dictation, I feel like I usually spend at least as much time correcting its mistakes as I do speaking the dictation itself. In some cases, that is still faster/easier than typing, but I would rather have a voice model that can work in about the same total amount of time without requiring constant corrections. If I speak for 30 seconds, then I can do other things for 30 seconds while my phone processes it… that might actually be preferable if it gets it right. Otherwise, I’ll be spending 30 seconds actively editing it anyways. Even an improvement on the number of edits required per dictation would be nice. Admittedly, I feel like Google and Microsoft already do a much better job here.
It could be interesting to use the tiny model to give a preview of the writing while the large model is taking its time, and then allow the user to tap on words that changed to see the predictions from the tiny model and correct back to them if they want. I was doing some experiments a few minutes ago, and on one audio clip, the tiny model wrote down a very literal interpretation of an uncommon sci-fi word, and that was more accurate than either the medium or the large models. The rest of the time, the larger models did better, as expected.
But, I don’t know. This is interesting to me, but I agree there could be issues with making is workable for real time transcription.
> Brute forcing the model with just traditional CPU instructions is fine, but… obviously going to be pretty slow.
It's not that simple. Many of the mobile ML accelerators are more targeted for conv net image workloads, and current-gen Intel and Apple CPUs have dedicated hardware to accelerate matrix math (which helps quite a bit here, and these instructions were in use in my tests).
Also, not sure which model they were using at 17x realtime on the 3090. (If it's one of the smaller models, that bodes even worse for non-3090 performance.) The 3090 is one of the fastest ML inference chips in the world, so it doesn't necessarily set realistic expectations.
There are also plenty of optimizations that aren't applied to the code we're testing, but I think it's fairly safe to say the Large model is likely to be slow on anything but a desktop-gpu-class accelerator just due to the sheer parameter size.