Search results
21 de sept. de 2022 · Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web. We show that the use of such a large and diverse dataset leads to improved robustness to accents, background noise and technical language.
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
13 de nov. de 2023 · Vamos a explicarte qué es Whisper, el sistema de inteligencia artificial de OpenAI para transcribir archivos de audio a texto.
Whisper is a Transformer based encoder-decoder model, also referred to as a sequence-to-sequence model. There are two flavours of Whisper model: English-only and multilingual. The English-only models were trained on the task of English speech recognition.
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition, translation, and language identification. This version runs only the most recent Whisper model, large-v3.
1 de jul. de 2024 · Desarrollado por OpenAI, Whisper AI es un modelo basado en redes neuronales convolucionales (CNN) diseñado específicamente para el reconocimiento de voz. A diferencia de muchas herramientas de voz a texto, Whisper AI es completamente gratuita, lo que la convierte en una opción atractiva tanto para particulares como para empresas.
En este artículo, te presentamos a Whisper de OpenAI, una solución de inteligencia artificial diseñada para trascribir audio a texto con una eficacia sorprendente.
