← Back to AI Models

Whisper Large v3

Speech recognition model for transcription

Overview

Speech recognition model for transcription The model has 1.5B parameters. It is an open-weight model released under the MIT licence.

Key Capabilities

Speech To Text — suited for tasks requiring speech to text proficiency
Transcription — suited for tasks requiring transcription proficiency
Multilingual — suited for tasks requiring multilingual proficiency

Recommended Use Cases

Audio Transcription
Meeting Notes
Voice Migration

Technical Specifications

Context Window: -1 tokens
Parameters: 1.5B
Open Weight: Yes
Licence: MIT
Release Date: November 06, 2023

Provider

Whisper Large v3 is developed by OpenAI. For the latest information, visit the official documentation.