Apple's new SpeechAnalyzer API, benchmarked against Whisper and its predecessor

Post by satvikpendem » Mon, Jul 13, 2026, 8:59 PM UTC

arjie wrote: post #94

jiehong wrote: post #64

Earlier quoted context omitted.

Also, this test is English-only, while a strong point of other models is to understand different languages without first having to say which one (so you don't need 3 different keyboard shortcuts if you wanna dictate in 3 languages day-to-day)

Does anyone have any experience with Mandarin STT? What's a good model for this? The use-case I have is subtitling of Mandarin speech.

Post by satvikpendem » Mon, Jul 13, 2026, 9:04 PM UTC

ChadNauseam wrote: post #50

satvikpendem wrote: post #34

Whisper is the wrong model to benchmark against, or rather, there are better models that are state of the art now like Nemotron and Parakeet both by Nvidia, as well as Mistral's Voxtral and Cohere Transcribe. However, what's funny is, RIP to a lot of the paid apps that simply wrap Whisper, I'm sure Apple will make a native GUI such as a recorder app for macOS that obviates the need for these wrappers, which everyone…

> there are better models that are state of the art now like Nemotron and Parakeet both by Nvidia Is parakeet state of the art? It always transcribes speech fragments for me, like if I stutter and say "m-m-m-map" parakeet will dutifully transcribe "m m m map". Which I guess could be a good thing or a bad thing depending on what you want. Whisper does not do that however. I do like cohere transcribe a lot.

Post by Danox » Mon, Jul 13, 2026, 9:08 PM UTC

drnick1 wrote: post #119

madeofpalk wrote: post #83

Earlier quoted context omitted.

Test it! Does it make network requests? Unplug the internet and see if it still works!

You are being naive. An Apple device makes dozens of network requests every minute or so to Apple. It is neigh on impossible to verify what is being requested or sent. Also unplugging the Internet and verifying that something still works does not mean the app won't phone home behind your back when it can. These things are designed to fail silently.

Post by arjie » Mon, Jul 13, 2026, 9:11 PM UTC

satvikpendem wrote: post #151

arjie wrote: post #94

Earlier quoted context omitted.

Does anyone have any experience with Mandarin STT? What's a good model for this? The use-case I have is subtitling of Mandarin speech.

MOSS-Transcribe-Diarize [0] is by a Chinese team so apparently it's quite good. Try it out here [1]. [0] https://huggingface.co/OpenMOSS-Team/MOSS-Transcribe-Diarize [1] https://huggingface.co/spaces/OpenMOSS-Team/MOSS-transcribe-...

Post by monster_truck » Mon, Jul 13, 2026, 9:14 PM UTC

wgm wrote: post #129

monster_truck wrote: post #127

Earlier quoted context omitted.

Why did you buy the cheap one, that's your own fault

At the time, there was very little advantage to buying the Pro model. Ironically, it's the first time I've ever bought the base model.