tesseract-lang

{
  "aliases": [],
  "alternatives": [
    "Tesseract (base engine)",
    "Paddleocr",
    "EasyOCR"
  ],
  "build_dependencies": [],
  "categories": [
    "ocr",
    "library"
  ],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [
    "tesseract"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Enables extra languages support for Tesseract",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:40:50+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "tesseract-lang",
  "github_default_branch": "main",
  "github_last_commit_at": "2024-08-01T19:42:06Z",
  "github_readme_excerpt": "# tessdata_fast \u2013 Fast integer versions of trained models\n\nThis repository contains fast integer versions of trained models for the [Tesseract Open Source OCR Engine](https://github.com/tesseract-ocr/tesseract).\n\nThese models only work with the LSTM OCR engine of Tesseract 4 and 5.\n\n- These are a speed/accuracy compromise as to what offered the best \"value for money\" in speed vs accuracy. \n- For some languages, this is still best, but for most not. \n- The \"best value for money\" network configuration was then integerized for further speed.\n- Most users will want to use these traineddata files to do OCR and these will be shipped as part of Linux distributions eg. Ubuntu 18.04.\n- Fine tuning/incremental training will **NOT** be possible from these `fast` models, as they are 8-bit integer. \n- When using the models in this repository, only the new LSTM-based OCR engine is supported. The legacy `tesseract` engine is not supported with these files, so Tesseract\u0027s oem modes \u00270\u0027 and \u00272\u0027 won\u0027t work with them.\n\n## Deprecated models\n\nThe former model `frk` has been renamed to `deu_latf` because the old name was never ISO compliant.\nA symbolic link from deu_latf.traineddata to frk.traineddata may help to migrate from the old name to the new one.\nHowever, all projects and distributions are encouraged to use only the new name.\nThe use of `frk` is deprecated and will not be supported in the future.\n\n## Two types of models\n\nThe repository contains two types of models,\n- those for a single language and\n- those for a single script supporting one or more languages.\n\nMost of the script models include English training data as well as the script, but not **Cyrillic**, as that would have a major ambiguity problem. \n\nOn Debian and Ubuntu, the language based traineddata packages are named `tesseract-ocr-LANG` where LANG is the three letter language code eg. tesseract-ocr-eng (English language), tesseract-ocr-hin (Hindi language), etc. \n\nOn Debian and Ubuntu, the script based traineddata pack",
  "github_repo": "tesseract-ocr/tessdata_fast",
  "github_stars": 604,
  "github_topics": [
    "ocr",
    "tesseract"
  ],
  "homepage": "https://github.com/tesseract-ocr/tessdata_fast/",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 8724,
  "installs_365d": 54320,
  "installs_90d": 23971,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "Apache-2.0",
  "llm_generated_at": "2026-06-20T23:44:32+00:00",
  "llm_model": "claude-haiku-4-5",
  "name": "tesseract-lang",
  "oldnames": [],
  "one_liner": "Language data files for Tesseract OCR engine, enabling optical character recognition in 100+ languages.",
  "optional_dependencies": [],
  "rank_30d": 385,
  "rank_365d": 643,
  "rank_90d": 456,
  "raw_hash": "d2fb7c4e3a79c182",
  "recommended_dependencies": [],
  "revision": 0,
  "ruby_source_path": "Formula/t/tesseract-lang.rb",
  "tap": "homebrew/core",
  "test_dependencies": [],
  "uses_from_macos": [],
  "version_head": null,
  "version_stable": "4.1.0",
  "versioned_formulae": [],
  "why_use_this": "Required runtime dependency if you\u0027re using Tesseract for OCR beyond English. Provides fast integer-quantized trained models optimized for speed/accuracy trade-off; supports only Tesseract 4+ LSTM engine (not legacy modes). Install alongside tesseract formula to unlock multi-language recognition."
}