Fact · Languages and accents
The Whisper repository says its turbo model is not trained for translation, and that you should use a multilingual model (tiny, base, small, medium or large) to translate non-English speech into English.
Checked against its source on October 16, 2026
In the source's own words
“However, the turbo model is not trained for translation tasks. If you need to translate non-English speech into English, use one of the multilingual models”
openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision, OpenAI, GitHub (OpenAI repository), 2023, README, Command-line usage.
Open the original- What it measures
- The README describes how to run Whisper from the command line and which model sizes support the translate task.
- What it does not show
- Model lineups change. The note describes the repository on the day we read it.