Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

get-inscribe.com

Post reply on HN
Print view View original

171–180 of 251 posts

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

#171

Post by ComputerGuru »

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…

Whisper v3 is still the best (by far) when it comes to poor quality input (say background audio from a security camera), though remains more susceptible to hallucination so it's a bit of a tradeoff.

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

#172

Post by thih9 »

> Apple's new SpeechAnalyzer is the most accurate on-device speech engine we tested. It beat every Whisper model we ship, including Whisper Small, on both the clean and the noisy half of LibriSpeech, while running roughly three times faster than Small.

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

#173

Post by arjie »

tapland wrote: post #170
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.

I use Systran/faster-whisper-medium for real-time subtitling, but you need to get used to the context it's used it and the weirdness it translates into. Parakeet has great mandarin>CN text, but running that + a translation model has been tricky and I never got it fast.

Thank you for this too. I am running in an offline scope so I don't need speed just quality. I'm willing to do it overnight as well if required.

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

#174

Post by port3000 »

cootsnuck wrote: post #167
port3000 wrote: post #44

I use Spokenly, offline-only mode with the Nvidia model. All local, totally free. Highly recommend

For just desktop, I use Handy (open source): https://handy.computer/ And yea, Nvidia's Parakeet v3 is good enough for my own just local transcription most of the time. When I need local transcription to be more reliable and I don't have the energy to proof read a long ramble, I still often just pop open chatGPT, dictate, cut, paste. But we're pretty much already to the point where local transcription models can repla…

Thanks will check it out, hadn't heard of it

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

#175

Post by hamza_q_ »

foobarqux wrote: post #108
parl_match wrote: post #99

Earlier quoted context omitted.

Apple likely needed a model that ran on their NPU natively. - parakeet usually runs on Bfloat16. NPU doesn't support that - CPU is not as fast as the NPU for these ops on A-series, and even on modern CPUs, there's a latency delay - Parakeet latency is fine but "fine" may not be good enough for Apple's UX team. - CPU increases power consumption over dedicated float blocks So I would say that Parakeet was a non-option…

Fluidaudio implements Parakeet on ANE. I'd like to know how SpeechAnalyzer compares in speed. https://github.com/FluidInference/FluidAudio

Recently contributed a patch to FluidAudio that sped up Parakeet V2 and V3 to 320x and 282x faster than real time, respectively:

https://github.com/FluidInference/FluidAudio/pull/507

That means one hour of audio transcribed in 11.25 and 12.75 seconds.

The Inscribe post doesn't give a speed factor for SpeechAnalyzer. However, this Argmax blog post reports 70:

https://www.argmaxinc.com/blog/apple-and-argmax

Based on that, FluidAudio is ~4.6x and ~4.0x faster.

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

#176

Post by tcoff91 »

mchusma wrote: post #105

I will plug Willow for mac recording. IMO it's basically to me a "better than perfect transcription" as it cleans things up and is almost instant. I liked Superwhisper but switched to Willow as it was a big difference. Its so good that I'm not sure that it's possible to get any better. Speech to text seems like basically a solved problem, if not now then definitely in 5 years. I don't know if any of these speech to t…

What isn't solved is domain-specific jargon with these tools. When i talk to my coding agent, i want to be able to speak the names of symbols and files and have it be aware of that stuff, like having LSP integration.

If I say 'useSuspenseQuery' I want it to come out as useSuspenseQuery not 'use suspense query'. Even if I had to say 'symbol useSuspenseQuery' to give a hint that i'm referencing a symbol, that would be fine.

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

#178

Post by akurilin »

anamexis wrote: post #100
akurilin wrote: post #87

Would this end up replacing the default iOS keyboard dictation functionality in iOS 27?

No, this is the current dictation functionality on iOS 26.

Do you happen to have any links that document this? I haven't been able to confirm.

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

#179

Post by 1vuio0pswjnm7 »

edude03 wrote: post #40
drnick1 wrote: post #23

If this isn't open source/weights and can't run locally, I don't see how this is a replacement for Whisper or other open models, e.g. within Home Assistant.

It's not open weight, but the point is to be an on device (and thus local, privacy preserving) option. The article mentions that as the caveat > What this means if you just want good transcription > If you are on a current iPhone or Mac, the best on-device transcription engine for English is already in the operating system, and the private option is no longer the compromise option

If already have current Mac or iPhone, and thereby implictly "trust Apple", then why would one need a "a local, privacy-preserving" option

If trust Apple, then no need for privacy from Apple

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

#180

Post by madeofpalk »

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.

This is Hacker News. Computers are knowable, tractable things. It is trivial to know if a process is making network requests.
Post reply on HN