{"id":19098478,"url":"https://github.com/winkjs/wink-eng-lite-model","last_synced_at":"2026-02-16T20:35:36.019Z","repository":{"id":45861615,"uuid":"264856181","full_name":"winkjs/wink-eng-lite-model","owner":"winkjs","description":"English lite language model for wink-nlp.","archived":false,"fork":false,"pushed_at":"2021-07-15T15:41:25.000Z","size":42,"stargazers_count":13,"open_issues_count":1,"forks_count":1,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-10-14T07:10:05.784Z","etag":null,"topics":["custom-entity-detection","english","model","named-entity-recognition","natural-language-processing","negation-handling","ner","nlp","pos-tagging","sentence-boundary-detection","sentiment-analysis","tokenization","winkjs","winknlp"],"latest_commit_sha":null,"homepage":"https://winkjs.org/wink-nlp/","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/winkjs.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2020-05-18T07:06:42.000Z","updated_at":"2025-04-27T23:40:50.000Z","dependencies_parsed_at":"2022-08-12T12:21:23.888Z","dependency_job_id":null,"html_url":"https://github.com/winkjs/wink-eng-lite-model","commit_stats":null,"previous_names":[],"tags_count":9,"template":false,"template_full_name":null,"purl":"pkg:github/winkjs/wink-eng-lite-model","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/winkjs%2Fwink-eng-lite-model","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/winkjs%2Fwink-eng-lite-model/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/winkjs%2Fwink-eng-lite-model/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/winkjs%2Fwink-eng-lite-model/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/winkjs","download_url":"https://codeload.github.com/winkjs/wink-eng-lite-model/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/winkjs%2Fwink-eng-lite-model/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29517617,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-16T18:37:19.720Z","status":"ssl_error","status_checked_at":"2026-02-16T18:36:46.920Z","response_time":115,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["custom-entity-detection","english","model","named-entity-recognition","natural-language-processing","negation-handling","ner","nlp","pos-tagging","sentence-boundary-detection","sentiment-analysis","tokenization","winkjs","winknlp"],"created_at":"2024-11-09T03:46:01.238Z","updated_at":"2026-02-16T20:35:35.988Z","avatar_url":"https://github.com/winkjs.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# wink-eng-lite-model\n**English lite language model for winkNLP**\n\n[\u003cimg align=\"right\" src=\"https://decisively.github.io/wink-logos/logo-title.png\" width=\"100px\" \u003e](https://winkjs.org/)\nThis is a pre-trained English language model for the winkjs NLP package — [winkNLP](https://winkjs.org/wink-nlp/). The lite model package has a size of ~890KB, which expands to about 2.4MB after installation. It is an open-source language model, released under the MIT license.\n\nIt contains models for the following NLP tasks:\n\n1. Tokenization\n2. Token's Feature Extraction\n3. Sentence Boundary Detection\n4. Negation Handling\n5. POS tagging\n6. Automatic mapping of British spellings to American\n7. Named Entity Recognition\n8. Sentiment Analysis\n9. Custom Entities Definition\n10. Stemming using Porter Stemmer Algorithm V2\n11. Lemmatization\n12. Readability statistics computation\n\n\n\n## Getting Started\n\n### Installation\nThe model must be installed along with the [wink-nlp](https://winkjs.org/wink-nlp/):\n\n```sh\n# Install wink-nlp\nnpm install wink-nlp --save\n# Install wink-eng-lite-model\nnode -e \"require( 'wink-nlp/models/install' )\" wink-eng-lite-model\n```\n\n### Example\nWe start by requiring the **wink-nlp** package and the **wink-eng-lite-model**. Then we instantiate wink-nlp using the language model:\n\n```javascript\n// Load \"wink-nlp\" package.\nconst winkNLP = require('wink-nlp');\n// Load english language model — light version.\nconst model = require('wink-eng-lite-model');\n// Instantiate wink-nlp.\nconst nlp = winkNLP(model);\n\n// Code for Hello World!\nvar text = 'Hello   World!';\nvar doc = nlp.readDoc(text);\nconsole.log(doc.out());\n// -\u003e Hello   World!\n```\n\n### Documentation\nLearn how to use this model with winkNLP from the following resources:\n- [Overview](https://winkjs.org/wink-nlp/) — introduction to winkNLP.\n- [Concepts](https://winkjs.org/wink-nlp/getting-started.html) — everything you need to know to get started.\n- [API Reference](https://winkjs.org/wink-nlp/read-doc.html) — explains usage of APIs with examples.\n- [Release history](https://github.com/winkjs/wink-eng-lite-model/releases) — version history along with the details of breaking changes, if any.\n\n## About model\n### Performance\nThe [winkNLP](https://winkjs.org/wink-nlp/) processes raw text at **\u003e525,000 tokens per second** with this model, when [benchmarked](https://github.com/bestiejs/benchmark.js) using \"Ch 13 of Ulysses by James Joyce\" on a 2.2 GHz Intel Core i7 machine with 16GB RAM. The benchmark covered the entire NLP pipeline — tokenization, sentence boundary detection, negation handling, sentiment analysis, part-of-speech tagging, and named entity extraction.\n\n### Tokenization\nWhile it is trained to process English language text, it can tokenize text containing other languages such as Hindi, French and German. Such tokens are tagged as **X** (foreign word) during pos tagging.\n\n### POS Tagging\nThe model follows the [Universal POS tags](https://universaldependencies.org/u/pos/) standards. It delivers an accuracy of **~94.7%** on a subset of WSJ corpus — this includes *tokenization of raw text prior to pos tagging*.\n\n### Named Entity Recognition (NER)\nThe model is trained to detect **CARDINAL**, **DATE**, **DURATION**,  **EMAIL**, **EMOJI**, **EMOTICON**, **HASHTAG**, **MENTION**, **MONEY**, **ORDINAL**, **PERCENT**, **TIME**, and **URL**.\n\n### Sentiment Analysis\nIt delivers a [f-score](https://en.wikipedia.org/wiki/F1_score) of **~84.5%**, when validated using Amazon Product Review [Sentiment Labelled Sentences Data Set](https://archive.ics.uci.edu/ml/machine-learning-databases/00331/) at [UCI Machine Learning Repository](https://archive.ics.uci.edu/ml/index.php).\n\n### Storage Structure\nThe model is contained in the standard [NPM tarball](https://docs.npmjs.com/cli-commands/pack.html) format. You can find it under the latest [release](https://github.com/winkjs/wink-eng-lite-model/releases). The model is stored in form of trained data in JSON and binary formats. Apart from the data, there is a tiny fraction of JS glue code, which is primarily used during model loading.\n\n\n## Need Help?\nIf you spot a bug and the same has not yet been reported, raise a new [issue](https://github.com/winkjs/wink-eng-lite-model/issues).\n\n## About wink\n[Wink](https://winkjs.org/) is a family of open source packages for **Natural Language Processing**, **Machine Learning** and **Statistical Analysis** in NodeJS. The code is **thoroughly documented** for easy human comprehension and has a **test coverage of ~100%** for reliability to build production grade solutions.\n\n\n## Copyright \u0026 License\nThe **wink-eng-lite-model** is copyright 2020-21 of [GRAYPE Systems Private Limited](https://graype.in/).\n\nIt is licensed under the terms of the MIT License.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwinkjs%2Fwink-eng-lite-model","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwinkjs%2Fwink-eng-lite-model","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwinkjs%2Fwink-eng-lite-model/lists"}