whisper

by openai · Developer Tools

Robust Speech Recognition via Large-Scale Weak Supervision

New0 ratings108,622 starsActive
Developer ToolsDeveloper ToolPython
↓ Download v20250625GitHub⚑ Report
whisper — image 1
whisper — image 2
1 / 2

About this project

Whisper [[Blog]](https://openai.com/blog/whisper) [[Paper]](https://arxiv.org/abs/2212.04356) [[Model card]](https://github.com/openai/whisper/blob/main/model-card.md) [[Colab example]](https://colab.research.google.com/github/openai/whisper/blob/master/notebooks/LibriSpeech.ipynb) 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. Approach A Transformer sequence-to-sequence model is trained on various speech processing tasks, including multilingual speech recognition, speech translation, spoken…

Technologies

Python

Project health

Actively maintained
Last updatelast week
Contributors82
Latest releasev20250625
Open issues & PRs146
LicenseMIT
On GitHubsince 2022

GitHub

108,622
stars
13,168
forks
82
contributors
146
open issues & PRs
Python
language
last week
last commit
View on GitHub ↗All releases ↗

Reviews

out of 5 · 0 ratings
★★★★★
0%
★★★★
0%
★★★
0%
★★
0%
0%
Sign in to write a review
No reviews yet
Be the first to review whisper.

Built by

openai
Imported from GitHub · not yet claimed on GitPalace
View developer pageSign in with GitHub to claim

Maintain openai/whisper? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like