{"id":13695688,"url":"https://github.com/emres/turkish-deasciifier","last_synced_at":"2025-12-17T10:47:06.683Z","repository":{"id":56669654,"uuid":"575817","full_name":"emres/turkish-deasciifier","owner":"emres","description":"Turkish deasciifier in Python based on Deniz Yüret's turkish-mode for Emacs","archived":false,"fork":false,"pushed_at":"2025-09-18T19:58:11.000Z","size":223,"stargazers_count":151,"open_issues_count":2,"forks_count":23,"subscribers_count":11,"default_branch":"master","last_synced_at":"2025-09-18T22:10:23.504Z","etag":null,"topics":["deasciifier","diacritics","diacritics-reconstruction","diacritics-restoration","nlp","nlp-library","python","turkish","turkish-nlp"],"latest_commit_sha":null,"homepage":"https://ileriseviye.wordpress.com/tag/turkish-deasciifier/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/emres.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2010-03-23T15:22:27.000Z","updated_at":"2025-09-18T19:58:15.000Z","dependencies_parsed_at":"2022-08-15T23:00:40.273Z","dependency_job_id":null,"html_url":"https://github.com/emres/turkish-deasciifier","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/emres/turkish-deasciifier","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/emres%2Fturkish-deasciifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/emres%2Fturkish-deasciifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/emres%2Fturkish-deasciifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/emres%2Fturkish-deasciifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/emres","download_url":"https://codeload.github.com/emres/turkish-deasciifier/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/emres%2Fturkish-deasciifier/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":27781933,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-12-17T02:00:08.291Z","response_time":55,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["deasciifier","diacritics","diacritics-reconstruction","diacritics-restoration","nlp","nlp-library","python","turkish","turkish-nlp"],"created_at":"2024-08-02T18:00:32.350Z","updated_at":"2025-12-17T10:47:06.670Z","avatar_url":"https://github.com/emres.png","language":"Python","funding_links":[],"categories":["Libraries"],"sub_categories":["Python"],"readme":"\n# turkish-deasciifier: Turkish deasciifier\n\nThis is a **deasciifier** Python library and command line utility for Turkish that solves the problem of **diacritics restoration** (also known as **diacritics reconstruction**). It takes a Turkish string containing only\nASCII characters (that is, without proper diacritics) and replaces the relevant characters with their corresponding\nTurkish letters.\n\nThe web-based, online version of this system is available at:\n\n~~http://turkceyap.appspot.com~~ (I'm currently too busy to fix it, please use https://deasciifier.com/ instead!)\n\nKeep in mind that diacritics restoration (deasciification) for Turkish doesn't work 100% of the time; it is an active research topic! Still, this library is good enough for many practical purposes, and served many people and projects in the last 15 years.\n\nThis system is based on the [turkish-mode](http://github.com/emres/turkish-mode) for [GNU Emacs](https://www.gnu.org/software/emacs/) by [Prof. Deniz Yüret](http://www.denizyuret.com/).\n\n# Table of Contents\n1. [Installation](#installation)\n2. [Example Python Library Usage](#example-python-library-usage)\n3. [Example CLI (Command Line Interface) Usage](#example-cli-command-line-interface-usage)\n4. [Other Programming Languages and Systems](#other-programming-languages-and-systems)\n5. [Advanced Research](#advanced-research)\n\n## Installation\n### Python 3\nFor now, _the recommended way_ to install is to use [pip](https://pypi.org/project/pip/) and install direcly from the [project's GitHub repository](https://github.com/emres/turkish-deasciifier):\n\n```shell\npip install git+https://github.com/emres/turkish-deasciifier.git\n```\n\n### Python 2\nKeep in mind that [switching to Python 3 is strongly recommended](https://www.python.org/doc/sunset-python-2/)! If you insist on using Python 2.x, you can install using the following command:\n\n```shell\npip install Turkish-Deasciifier\n```\n\n## Example Python Library Usage\n### Python 3\n```python\nfrom turkish.deasciifier import Deasciifier\n\nmy_ascii_turkish_txt = \"Opusmegi cagristiran catirtilar.\"\ndeasciifier = Deasciifier(my_ascii_turkish_txt)\nmy_deasciified_turkish_txt = deasciifier.convert_to_turkish()\nprint(my_deasciified_turkish_txt)\n```\n\n### Python 2\nKeep in mind that [switching to Python 3 is strongly recommended](https://www.python.org/doc/sunset-python-2/)! If you insist on using Python 2.x, you can use the library in the following manner: \n\n```python\nfrom turkish.deasciifier import Deasciifier\n\nmy_ascii_turkish_txt = \"Opusmegi cagristiran catirtilar.\"\ndeasciifier = Deasciifier(my_ascii_turkish_txt.decode(\"utf-8\"))\nmy_deasciified_turkish_txt = deasciifier.convert_to_turkish()\nprint my_deasciified_turkish_txt.encode(\"utf-8\")\n```\t\t\n\n\n### Example CLI (Command Line Interface) Usage\n#### Python 3\nExample tested in a Bash shell:\n\n```shell\n$ echo \"Opusmegi cagristiran catirtilar.\" | turkish-deasciify\n$ cat somefile.txt | turkish-deasciify\n```\n\n#### Python 2\nKeep in mind that [switching to Python 3 is strongly recommended](https://www.python.org/doc/sunset-python-2/)!\n\nExample tested in a Bash shell:\n\n```shell\n$ echo \"Opusmegi cagristiran catirtilar.\" | turkish-deasciify-python2\n$ cat somefile.txt | turkish-deasciify-python2\n```\n\n### Other Programming Languages and Systems\n\n* Java: [https://github.com/ahmetb/turkish-deasciifier-java](https://github.com/ahmetb/turkish-deasciifier-java)\n* Perl: [https://metacpan.org/pod/release/BURAK/Lingua-TR-ASCII-0.13/lib/Lingua/TR/ASCII.pm](https://metacpan.org/pod/release/BURAK/Lingua-TR-ASCII-0.13/lib/Lingua/TR/ASCII.pm)\n* Haskell:  [http://hackage.haskell.org/package/turkish-deasciifier](http://hackage.haskell.org/package/turkish-deasciifier)\n* Node.js: [https://github.com/f/deasciifier/](https://github.com/f/deasciifier/)\n* VIM: [https://github.com/joom/turkish-deasciifier.vim](https://github.com/joom/turkish-deasciifier.vim)\n* Emacs Lisp: [https://github.com/emres/turkish-mode](https://github.com/emres/turkish-mode) (also available as a [package in MELPA](https://melpa.org/#/turkish))\n* Swift: [https://github.com/armish/TurkishDeasciifier](https://github.com/armish/TurkishDeasciifier)\n\n## Advanced Research\nFor recent advanced scientific research articles, please see the following:\n\n* [The Deceptively Complex World of Turkish Diacritics: A Neural Network Journey](https://ergoso.me/turkish/neural/network/github/diacritics/macos/app/swift/python/2025/09/17/turkish-diacritic-restoration.html)\n    * [https://github.com/armish/nokta-ai](https://github.com/armish/nokta-ai)\n* Diacritic Restoration Using Recurrent Neural Network\n    * Paper: https://github.com/aysnrgenc/TurkishDeasciifier/blob/master/diacritic-restoration-recurrent.pdf\n    * Code: https://github.com/aysnrgenc/TurkishDeasciifier\n    * Data sets: https://github.com/aysnrgenc/TurkishDeasciifier/tree/master/data\n* Diacritics Restoration Using Neural Networks\n    * Paper: [https://www.aclweb.org/anthology/L18-1247.pdf](https://www.aclweb.org/anthology/L18-1247.pdf)\n    * Code: [https://github.com/arahusky/diacritics_restoration](https://github.com/arahusky/diacritics_restoration)\n    * Data sets: [Corpus for training and evaluating diacritics restoration systems](https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-2607)\n* Diacritic restoration of Turkish tweets with word2vec\n    * Paper: [https://www.sciencedirect.com/science/article/pii/S2215098618308668](https://www.sciencedirect.com/science/article/pii/S2215098618308668)\n* Vowel and Diacritic Restoration for Social Media Texts\n    * Paper: [https://www.aclweb.org/anthology/W14-1307/](https://www.aclweb.org/anthology/W14-1307/)\n    * Full text (PDF): [https://www.aclweb.org/anthology/W14-1307.pdf](https://www.aclweb.org/anthology/W14-1307.pdf)\n    * Web demo: [http://tools.nlp.itu.edu.tr/Deasciifier](http://tools.nlp.itu.edu.tr/Deasciifier)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Femres%2Fturkish-deasciifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Femres%2Fturkish-deasciifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Femres%2Fturkish-deasciifier/lists"}