#speech

Show HN: Teach a speech model (en) a name by saying it once, on your Mac

I wanted to see if a speech model could spell a name better if it heard it, not just read it. Most STT tools handle custom words as text (keyterm list, fixing transcript after with llm, etc). So I trained an adapter to try it, specifically a LoRA on Qwen3-ASR 1.7b (see benchmark). This LoRA transcribes words only after it hears a recording of each of your custom words. To make this model easier to use in day-to-day life, we also built Detail Keeper. It's a Mac app where you can put this adapter to use by specifying difficult-to-transcribe-correctly words and then having them picked up correctl

Show HN · EN

Subvocal’s glasses turn your silent speech into text at...

Subvocal’s glasses turn your silent speech into text at 200 wpm — it measures mouth movements with radar? Like many things these days, this is very technically interesting but also creepy and dystopian.

Kottke · EN

Nemotron 3.5 Transcribe

Intelligent Transcription with a Speech LLM Discussion | Link

Product Hunt · EN