OpenAI's open-source speech recognition model for any language. When Korean users type 위스퍼 (wi-seu-peo) on a QWERTY keyboard still set to English, the keys produce dnltmvj. This page explains the mapping and how to make the most of Whisper as a Korean user.
On the standard Korean 두벌식 (2-set) layout, typing while the input is still in English mode maps each Korean character to a specific QWERTY key. The Korean name 위스퍼 is typed as these keys:
Put together: 위스퍼 typed in English mode spells dnltmvj. Korean users searching for Whisper who forget to press the 한/영 key first land on this search term — and Google's intent matching now routes many of these searches to Whisper results.
Whisper is an open-source automatic speech recognition (ASR) model from OpenAI, trained on 680,000 hours of multilingual audio. It transcribes and translates speech in over 100 languages with high accuracy and is particularly strong on noisy audio and accented speech. Whisper is freely downloadable and can be run locally or accessed via the OpenAI API.
Whisper's Korean transcription accuracy is excellent, making it the go-to tool for Korean podcast transcription, 회의 (meeting) recording to text, and subtitle generation for Korean video content. Korean indie filmmakers use it to auto-generate SRT subtitle files. Language learning apps targeting Korean have integrated Whisper for pronunciation checking and listening comprehension exercises.