C.W.K.
Stream
Quiz · 4 questions

👂 Hearing on Apple Silicon

On-device speech-to-text, and the traps that make it sound broken

Level 0Unlit
0 XP0/36 lessons0/12 achievements
0/100 XP to next level100 XP to go0% complete

Quiz

01Why is on-device STT the load-bearing choice for Firekeeper, beyond just 'privacy is nice'?
02WhisperKit's default DecodingOptions produced 'Korean dictation is broken' bug reports. What was actually happening?
03Apple's SpeechAnalyzer is fast and on-device. Why isn't it Firekeeper's default engine for Dad's speech?
04Whisper-family models are batch-oriented, but dictation wants real-time preview. What's the right way to fake streaming?
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.