Fact · Dictation software
OpenAI's Whisper maintainers announced the large-v3 model on November 6, 2023.
Quote found word for word on the live source, last checked October 19, 2026
In the source's own words
“Nov 6, 2023 Maintainer We're pleased to announce the latest iteration of Whisper, called large-v3”
large-v3 release (openai/whisper discussion #1762), OpenAI whisper maintainers, GitHub, openai/whisper repository, 2023, Release post dated Nov 6, 2023.
Open the original- What it measures
- The post is the project maintainer's own release announcement in the official repository. It says large-v3 has the same architecture as the earlier large models, except for 128 Mel frequency bins instead of 80 and a new language token for Cantonese.
- What it does not show
- The post gives the name, the date and the architecture changes only. Benchmark claims for large-v3 come from other sources.
In the data
A row of History of Dictation Software: A Dated Timeline, as Whisper large-v3, Nov 2023: 2,023 year.
- Event
- Model release
- Product
- Whisper large-v3
- Maker
- OpenAI
- Date
- 2023-11-06
- Kind
- Speech model