{"data":{"slug":"openai-whisper","name":"whisper","tagline":"Robust Speech Recognition via Large-Scale Weak Supervision","github_url":"https://github.com/openai/whisper","owner":"openai","repo":"whisper","owner_avatar_url":"https://avatars.githubusercontent.com/u/14957082?v=4","primary_language":"Python","stars":104461,"forks":12725,"topics":[],"archived":false,"github_pushed_at":"2026-04-15T16:32:15+00:00","url":"https://www.graphcanon.com/tools/openai-whisper","markdown_url":"https://www.graphcanon.com/tools/openai-whisper.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openai-whisper","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openai-whisper","description":"Robust Speech Recognition via Large-Scale Weak Supervision","homepage_url":null,"license":"MIT","open_issues":134,"watchers":751,"ai_summary":"Whisper is a general-purpose speech recognition model developed by OpenAI. It can perform multilingual speech recognition, speech translation, spoken language identification, and voice activity detection.","readme_excerpt":"# Whisper\n\n[[Blog]](https://openai.com/blog/whisper)\n[[Paper]](https://arxiv.org/abs/2212.04356)\n[[Model card]](https://github.com/openai/whisper/blob/main/model-card.md)\n[[Colab example]](https://colab.research.google.com/github/openai/whisper/blob/master/notebooks/LibriSpeech.ipynb)\n\nWhisper 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.\n\n\n## Approach\n\n\n\nA 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. The multitask training format uses a set of special tokens that serve as task specifiers or classification targets.\n\n\n## Setup\n\nWe used Python 3.9.9 and [PyTorch](https://pytorch.org/) 1.10.1 to train and test our models, but the codebase is expected to be compatible with Python 3.8-3.11 and recent PyTorch versions. The codebase also depends on a few Python packages, most notably [OpenAI's tiktoken](https://github.com/openai/tiktoken) for their fast tokenizer implementation. You can download and install (or update to) the latest release of Whisper with the following command:\n\n    pip install -U openai-whisper\n\nAlternatively, the following command will pull and install the latest commit from this repository, along with its Python dependencies:\n\n    pip install git+https://github.com/openai/whisper.git \n\nTo update the package to the latest version of this repository, please run:\n\n    pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git\n\nIt also requires the command-line tool [`ffmpeg`](https://ffmpeg.org/) to be installed on your system, which is available from most package managers:\n\n```bash\n# on Ubuntu or Debian\nsudo apt update && sudo apt install ffmpeg\n\n# on Arch Linux\nsudo pacman -S ffmpeg\n\n# on MacOS using Homebrew (https://brew.sh/)\nbrew install ffmpeg\n\n# on Windows using Chocolatey (https://chocolatey.org/)\nchoco install ffmpeg\n\n# on Windows using Scoop (https://scoop.sh/)\nscoop install ffmpeg\n```\n\nYou may need [`rust`](http://rust-lang.org) installed as well, in case [tiktoken](https://github.com/openai/tiktoken) does not provide a pre-built wheel for your platform. If you see installation errors during the `pip install` command above, please follow the [Getting started page](https://www.rust-lang.org/learn/get-started) to install Rust development environment. Additionally, you may need to configure the `PATH` environment variable, e.g. `export PATH=\"$HOME/.cargo/bin:$PATH\"`. If the installation fails with `No module named 'setuptools_rust'`, you need to install `setuptools_rust`, e.g. by running:\n\n```bash\npip install setuptools-rust\n```\n\n\n## Available models and languages\n\nThere are six model sizes, four with English-only versions, offering speed and accuracy tradeoffs.\nBelow are the names of the available models and their approximate memory requirements and inference speed relative to the large model.\nThe relative speeds below are measured by transcribing English speech on a A100, and the real-world speed may vary significantly depending on many factors including the language, the speaking speed, and the available hardware.\n\n|  Size  | Parameters | English-only model | Multilingual model | Required VRAM | Relative speed |\n|:------:|:----------:|:------------------:|:------------------:|:-------------:|:--------------:|\n|  tiny  |    39 M    |     `tiny.en`      |       `tiny`       |     ~1 GB     |      ~10x      |\n|  base  |    74 M    |     `base.en`      |       `base`       |     ~1 GB     |      ~7x       |\n| small  |   244 M    |     `small.en`     |   ","github_created_at":"2022-09-16T20:02:54+00:00","created_at":"2026-07-07T22:37:48.600733+00:00","updated_at":"2026-07-07T22:37:50.756386+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"transformer","name":"transformer"},{"slug":"multitasking-model","name":"multitasking model"},{"slug":"weak-supervision","name":"weak supervision"}]}}