Of these only Parakeet is <1B, it looks better than Apple's model, however it's not builtin. I wonder how it compares on latency and efficiency.

Parakeet is incredibly fast and accurate even on CPU, and it supports streaming now also in TDT3.

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 for Apple to ship, although it should be in the benchmarks anyways!

Fluidaudio implements Parakeet on ANE. I'd like to know how SpeechAnalyzer compares in speed.

	▲	hamza_q_ 27 minutes ago \| parent \| next [-]
		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.
	▲	foobarqux 5 hours ago \| parent \| prev [-]
		Just tried test using yap on a single ~1hr mp3: yap/Speechanalyzer is about 50% slower than fluidaudio on M1. yap interface is nicer though. https://github.com/finnvoor/yap