> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/openai/whisper/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Robust speech recognition via large-scale weak supervision

<img className="block dark:hidden" src="https://raw.githubusercontent.com/openai/whisper/main/approach.png" alt="Whisper Approach" />

<img className="hidden dark:block" src="https://raw.githubusercontent.com/openai/whisper/main/approach.png" alt="Whisper Approach" />

## What is Whisper?

Whisper is a general-purpose speech recognition model developed by OpenAI. It is trained on a large dataset of diverse audio and is a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.

A Transformer sequence-to-sequence model is trained on various speech processing tasks, including multilingual speech recognition, speech translation, spoken language identification, and voice activity detection. These tasks are jointly represented as a sequence of tokens to be predicted by the decoder, allowing a single model to replace many stages of a traditional speech-processing pipeline.

## Key Features

<CardGroup cols={2}>
  <Card title="Multilingual Recognition" icon="globe">
    Transcribe speech in 99+ languages with high accuracy across diverse accents and dialects
  </Card>

  <Card title="Speech Translation" icon="language">
    Translate speech from any supported language directly into English text
  </Card>

  <Card title="Multiple Model Sizes" icon="layer-group">
    Choose from 6 model sizes (tiny to turbo) to balance speed and accuracy for your use case
  </Card>

  <Card title="Simple API" icon="code">
    Easy-to-use Python API and command-line interface for quick integration
  </Card>
</CardGroup>

## Available Models

Whisper offers six model sizes with varying speed and accuracy tradeoffs:

| Size   | Parameters | English-only | Multilingual | Required VRAM | Relative Speed |
| ------ | ---------- | ------------ | ------------ | ------------- | -------------- |
| tiny   | 39 M       | `tiny.en`    | `tiny`       | \~1 GB        | \~10x          |
| base   | 74 M       | `base.en`    | `base`       | \~1 GB        | \~7x           |
| small  | 244 M      | `small.en`   | `small`      | \~2 GB        | \~4x           |
| medium | 769 M      | `medium.en`  | `medium`     | \~5 GB        | \~2x           |
| large  | 1550 M     | N/A          | `large`      | \~10 GB       | 1x             |
| turbo  | 809 M      | N/A          | `turbo`      | \~6 GB        | \~8x           |

<Note>
  The `.en` models for English-only applications tend to perform better, especially for the `tiny.en` and `base.en` models. The `turbo` model is an optimized version of `large-v3` that offers faster transcription speed with minimal degradation in accuracy.
</Note>

<Warning>
  The `turbo` model is not trained for translation tasks. If you need to translate non-English speech into English, use one of the multilingual models (`tiny`, `base`, `small`, `medium`, `large`) instead.
</Warning>

## Getting Started

<CardGroup cols={2}>
  <Card title="Installation" icon="download" href="/installation">
    Install Whisper and its dependencies on your system
  </Card>

  <Card title="Quickstart" icon="bolt" href="/quickstart">
    Start transcribing audio in minutes with CLI and Python examples
  </Card>
</CardGroup>

## Resources

<CardGroup cols={3}>
  <Card title="Research Paper" icon="file-lines" href="https://arxiv.org/abs/2212.04356">
    Read the technical paper on arXiv
  </Card>

  <Card title="Blog Post" icon="newspaper" href="https://openai.com/blog/whisper">
    Learn more from the official OpenAI blog
  </Card>

  <Card title="Model Card" icon="id-card" href="https://github.com/openai/whisper/blob/main/model-card.md">
    View detailed model specifications
  </Card>
</CardGroup>

## Python Compatibility

Whisper is compatible with Python 3.8-3.13 and recent PyTorch versions. The codebase was developed and tested with Python 3.9.9 and PyTorch 1.10.1.