Fact · Speech recognition
openai-whisper saves its model files to ~/.cache/whisper unless you set a different folder with --model_dir.
Checked against its source on October 17, 2026
In the source's own words
“the path to save model files; uses ~/.cache/whisper by default”
whisper/transcribe.py: decoding defaults and command-line options (openai/whisper), OpenAI, GitHub (openai/whisper), 2026, Command-line options (--model_dir).
Open the original- What it measures
- The help text is printed by whisper --help. Models download automatically the first time you use one.
- What it does not show
- The location is set in the code. A different install method may use another folder.