openai-whisper

{
  "aliases": [],
  "alternatives": [
    "SpeechRecognition",
    "Mozilla DeepSpeech",
    "Kaldi",
    "Vosk"
  ],
  "build_dependencies": [
    "cmake",
    "pkgconf",
    "rust"
  ],
  "categories": [
    "ai",
    "ml",
    "language-runtime",
    "binding"
  ],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [
    "certifi",
    "ffmpeg",
    "llvm@20",
    "python@3.14",
    "pytorch"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "General-purpose speech recognition model",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:40:55+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "openai-whisper",
  "github_default_branch": "main",
  "github_last_commit_at": "2026-04-15T16:32:15Z",
  "github_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![Approach](https://raw.githubusercontent.com/openai/whisper/main/approach.png)\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\u0027s 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.",
  "github_repo": "openai/whisper",
  "github_stars": 103191,
  "github_topics": [],
  "homepage": "https://github.com/openai/whisper",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 6186,
  "installs_365d": 102730,
  "installs_90d": 33007,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "MIT",
  "llm_generated_at": "2026-06-20T23:45:19+00:00",
  "llm_model": "claude-haiku-4-5",
  "name": "openai-whisper",
  "oldnames": [],
  "one_liner": "General-purpose speech recognition model for multilingual recognition, translation, and language identification via Python.",
  "optional_dependencies": [],
  "rank_30d": 512,
  "rank_365d": 411,
  "rank_90d": 368,
  "raw_hash": "b1910eb8e1684bcf",
  "recommended_dependencies": [],
  "revision": 5,
  "ruby_source_path": "Formula/o/openai-whisper.rb",
  "tap": "homebrew/core",
  "test_dependencies": [],
  "uses_from_macos": [],
  "version_head": "HEAD",
  "version_stable": "20250625",
  "versioned_formulae": [],
  "why_use_this": "Whisper handles multiple speech tasks (transcription, translation, language ID) in one model, trained on 680k hours of diverse multilingual audio. Use it when you need robust, offline-capable speech recognition that works across languages without building a complex pipeline. Heavier than lightweight models but more accurate and versatile."
}