Whisper: OpenAI's Open-Source Speech Recognition Model
June 6, 2026
Whisper is OpenAI's open-source speech recognition model trained on 680,000 hours of multilingual web audio using weak supervision. It supports transcription and translation across multiple languages with models ranging from 39M to 1.5B parameters.
HOW THIS AFFECTS YOU
●
builderEstablished open-source option for speech-to-text; no new releases or updates here, just repo re-trending.