Fact · Dictation in your apps
1550million parameters
The large Whisper model has 1,550 million parameters.
Checked against its source on October 17, 2026
In the source's own words
“large 1550 M N/A large ~10 GB 1x”
openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision, OpenAI, GitHub (OpenAI repository), 2023, Available models and languages table.
Open the original- What it measures
- The model table in the README of the openai/whisper repository on GitHub, read on 2026-10-17.
- What it does not show
- The table lists the English-only and multilingual models. Speed values are measured on one GPU and vary with language and hardware.