Aller au contenu
Atlas de l'IA

Whisper

Transcrit la parole en plusieurs langues et la traduit en anglais

OpenAI Modèle Poids ouverts
entréeAudioTexte

Le texte intégral est présenté en anglais ; le titre et le résumé sont localisés.

CE QUE C'EST

Whisper is a speech-recognition model OpenAI released in September 2022, with open weights and code. It was trained on roughly 680,000 hours of multilingual, multitask audio from the web and frames transcription, translation and language identification as a single sequence-to-sequence problem. The model is an encoder–decoder that takes 30-second audio segments as input. It shipped in several sizes from tiny to large, with the large version at about 1.55 billion parameters.

Pourquoi il compte

With open weights it made multilingual speech recognition broadly usable, becoming the default choice in many speech apps and transcription tools, and stands as a leading example of weak supervision with large-scale data in speech.

Caractéristiques clés

Parameters
About 1.55B (large)
Training data
About 680,000 hours of audio
Languages
About 99
Open weights
Yes (MIT licence)
Architecture
Encoder–decoder transformer

Capacités

Concepts liés

Produits comparables