openai/whisper

Robust Speech Recognition via Large-Scale Weak Supervision

Python108K stars13K forks+155 today

What it does

Whisper is a versatile speech recognition model developed by OpenAI, capable of multilingual transcription, translation, and language identification. It leverages large-scale weak supervision for robust performance across diverse audio datasets.

Star history

Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.

Tracking

Last trending: 2026-06-06

Creator kit

Hook

Transform your audio content into text with ease using Whisper, the powerful speech recognition model from OpenAI. 🎤💻 #WhisperModel

Content angles

Create a tutorial on how to use Whisper for multilingual transcription.
Analyze the performance of Whisper compared to other speech recognition models in various languages.
Develop an interactive demo showcasing Whisper's capabilities in real-time speech translation.

Who should care

AI researchers, developers interested in natural language processing and speech technology, content creators looking to automate text generation from audio.