Audio model

Whisper

Whisper is OpenAI’s open-source general-purpose speech recognition model for transcription, translation, and language identification. It is a multitask Transformer sequence-to-sequence system trained on large-scale diverse audio, with multilingual support and model sizes ranging from tiny to large plus a faster turbo variant.

Type
Audio
Weights
Open
Downloads
1.6M
Likes
448
Pipeline
automatic speech recognition
License
apache-2.0

Model hub

openai/whisper-tiny

Repo
openai/whisper-tiny
Library
transformers
Access
Public
Technical tags and languages
tf en zh de es ru ko fr ja pt tr pl ca nl ar sv it id hi fi vi he uk el ms cs ro da hu ta no th transformers pytorch jax safetensors whisper automatic-speech-recognition audio hf-asr-leaderboard
Open on Hugging Face

Related tools

4

More from OpenAI

11

About OpenAI

1

OpenAI develops and deploys general-purpose artificial intelligence models, products, and developer platforms.

Tools using Whisper

24