[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-96163":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":16,"stars30d":17,"stars90d":16,"forks30d":16,"starsTrendScore":16,"compositeScore":18,"rankGlobal":10,"rankLanguage":10,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},96163,"text-humanizer","SpaceDudem\u002Ftext-humanizer","SpaceDudem","text-humanizer is an open-source project designed to convert text generated by AI to its \"humanized\" version. Bypasses the most of AI detectors such as Turnitin or GPTZero","",null,"Python",455,103,39,1,0,224,6.05,"MIT License",false,"main",true,[24,25,5],"ai-humanizer","gpt-zero","2026-09-21 02:04:30","# text-humanizer\r\n\u003Cimg width=\"1090\" height=\"291\" alt=\"image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Ffdf5c218-b868-4d4f-824f-99632ec0af66\" \u002F>\r\n\r\n\r\n\r\n\r\n![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg) ![Python](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.6%2B-blue)\r\n\u003Cp align=\"center\">\r\n  English | \u003Ca href=\"README-zh.md\">中文\u003C\u002Fa>\r\n\u003C\u002Fp>\r\n\r\n# Overview\r\ntext-Humanizer is a completely free open-sourced project designed to humanize AI-generated text through a multilingual LLM-powered rewriting pipeline. By leveraging large language models for semantic-preserving text transformation, the system rewrites content with more natural sentence structures, varied linguistic patterns, and improved stylistic diversity while maintaining the original meaning across multiple languages.\r\n\r\n## Features\r\n- Preserves original meaning while improving text naturalness\r\n- Bypasses most of AI-detectors\r\n- Fully free and open-source\r\n- Adaptable to different writing styles and tones\r\n- 8 languages supported(en, ja, zh, ko, de, fr, es.)\r\n# How it works\r\n\r\n**Step 1 - LLM Rewrite (DeepSeek)**\r\n\r\nText is rewritten using the DeepSeek LLM to generate a semantically equivalent version with modified sentence structures, phrasing, and information flow. During this stage, the model also translates the content into Chinese as an intermediate representation to introduce structural variation and reduce original language patterns.\r\n\r\n**Step 2 - Google Translation (EN → TR)**\r\n\r\nThe output from Step 1 is translated into Turkish using Google Translate. This stage introduces additional syntactic distortion and cross-lingual variation based on rule-based and statistical translation differences.\r\n\r\n**Step 3 - DeepL Translation (Optional, TR → JA)**\r\n\r\nIf a DeepL API key is provided, the Turkish text is further translated into Japanese using DeepL API. This optional step improves linguistic diversity and adds a second independent translation engine into the pipeline.\r\n\r\n**Step 4 - Final Reconstruction (DeepSeek)**\r\nThe resulting text is translated back into the original input language using the DeepSeek LLM. This step removes accumulated translation artifacts, restores readability, and reconstructs natural sentence flow while preserving semantic meaning.\r\n\r\n\u003Cp align=\"center\">\r\n\u003Cimg width=\"850\" height=\"400\" alt=\"image\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F89c0823c-d324-42bd-b820-04f8161bfc69\" \u002F>\r\n\u003C\u002Fp>\r\n\r\n# Quick start(Windows\u002FLinux\u002FMacOS)\r\n\r\n```bash\r\ngit clone https:\u002F\u002Fgithub.com\u002FSpaceDudem\u002Ftext-humanizer.git\r\ncd text-humanizer\r\npip install -r requirements.txt\r\n\r\ncopy .\\config\\config.example.toml .\\config.toml #config file creation\r\n\r\npython main.py # run humanizer\r\n```\r\n## Configuration\r\nEdit `config.toml` to configurate text-humanizer:\r\n\r\n| Option        | Description                                   |\r\n|--------------|-------------------------------------------------|\r\n| `target_language`  | Which language to use used for output\u002Finput(en, ja, zh, ko, de, fr, es)         |\r\n| `deepseek_api_key` | Your DeepSeek API key               |\r\n| `deepl_api_key`   | Your DeepL API key(optional)                            |\r\n| `base_url`  | Override API base url(empy = provider default)               |\r\n| `model` | Model slug(empty = provider default)    |\r\n| `temperature` | LLM temperature(1.3 recommended)    |\r\n\r\n\r\n# License\r\n[MIT](LICENSE) License.\r\n\r\n","text-humanizer 是一个开源的AI文本人工润色工具，用于将AI生成文本重写为更自然、更具人类写作风格的版本。其核心采用多阶段LLM与跨语言翻译协同的语义保持型改写流程：先经DeepSeek模型语义重述并中文化，再经Google Translate转土耳其语，可选经DeepL转日语，最后由DeepSeek回译还原目标语言，在保留原意前提下提升句式多样性、语言流畅性与风格自然度，支持8种语言。适用于需降低AI检测识别率的学术写作辅助、内容创作合规优化等场景。",2,"2026-09-11 02:30:08","CREATED_QUERY"]