Whisper

General-purpose speech recognition model for transcription and translation

BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

OpenAI's past year

26 release days in the past year, about one every 14 days. The next is expected around Nov 28, 2026. Forecasts ↗

DecJanFebMarAprMayJunJulAugSepOctNov

Specifications

RELEASE DATESep 21, 2022
WEIGHTSClosed weights
CONTEXT WINDOWNot listed
MAX OUTPUT0
REASONINGNot listed
TOOL CALLINGNot listed
INPUTSaudio
OUTPUTStext

Models.dev record ↗

Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.