Fact · Dictation software
1550million parameters
The largest Whisper model, large, has 1,550 million parameters and needs about 10 GB of memory.
Checked against its source on October 16, 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 same table; large has no English-only version and is the slowest model in the table.
- What it does not show
- The memory figure is an approximate requirement. Accuracy and speed depend on language and hardware.
Source
Used to calculate
Cited on
- Dictation Software: How to Choose the Right AppTopic
- Speech Recognition: What It Is and How Well It WorksTopic
- Transcription: How to Turn Audio and Video Into TextTopic
- How to Transcribe Audio to TextGuide
- Open-Source Dictation Software: Free Apps on GitHubGuide
- Offline Speech to Text on Windows: What WorksGuide
- On-Device vs Cloud Speech Recognition: The TradeoffsGuide
- Can an ESP32 or microcontroller do speech recognition?Question
- How do you use Whisper for dictation on Linux?Question