Official documentation
hayamimi (早耳) README, oboroge0 on GitHub
oboroge0, GitHub, 2026
Read the originalRead on October 21, 2026
- What it is
- The README of hayamimi, an open-source real-time speech-to-text tool that runs on CPU with no cloud API. It describes a language catalog of five routes plus 24 EU languages, each with a dedicated model, and a fallback model for other languages.
- How much weight it carries
- Written by the project's maker and read on 2026-10-21. The 29 is the README's own catalog count, not a tested support list; the README points to a separate comparison document for results by language.
Facts taken from this source
- The hayamimi README describes a language catalog of five routes (Japanese, Chinese, Korean, Cantonese and English) plus 24 EU languages, each sent to a dedicated model: 29 languages in all.
“5-route language catalog ja/zh/ko/yue/en+24 EU languages each go to a dedicated best-in-class model; everything else (~1600 languages) falls back to Meta's Omnilingual ASR” (README, Features table)