https://news.ycombinator.com/user?id=jobuildsstuffHacker News RSShttps://hnrss.org/hnrss v2.1.1Wed, 19 Aug 2026 00:55:22 +0000Answering your question from the small end: I picked my STT by testing self-correction handling. My tool cleans up spoken drafts, and the failure that mattered wasn't word accuracy, it was "meet Tuesday, no wait, Wednesday": a raw transcript of that is worse than useless, and models differ a lot in how gracefully downstream cleanup can recover. Your spontaneous-speech testing sounds close to this already. Do the boards score corrections and disfluencies specifically, or do they fold into overall accuracy?

]]>Tue, 18 Aug 2026 14:07:18 +0000https://news.ycombinator.com/item?id=49345850jobuildsstuffhttps://news.ycombinator.com/item?id=49345850https://news.ycombinator.com/item?id=49345850