Taiwanese Hokkien Transliterator and Tokeniser
-
Updated
Apr 25, 2026 - Python
Taiwanese Hokkien Transliterator and Tokeniser
A curated list of resources about the Hokchew / Foochow language. 閩東語福州話的資源整合列表。
Educational language-learning app for Hokkien, a low-resource language, featuring flashcards, quizzes, and generative AI!
Tools to help create and evaluate Hokkien Translations (aka Minnan, Taiwanese, Hoklo, Southern Min, iso: nan).
桃橘(THOKIT,Tong-uán Hokkien Orthography toolKIT)
Taiwanese Hokkien Transliterator and Tokeniser
Taiwanese Hokkien (Taigi) speech-to-text transcriber - MediaTek Breeze-ASR-26 with faster-whisper, tuned for RTX 3050 4GB low-VRAM GPUs. Gradio UI, CLI, Docker, SRT/VTT/TXT/JSON.
Splits zh_TW/zh_CN input, looks up each part in Hokkien dictionary, then merges dict entries and original input back to a Mandarin -> Hokkien translation prompt - LLMs without Hokkien knowledge can learn from the prompt and give a decent translation
Hokkien & Teochew dataset, all in ONE.
福建話拍字方案,包含漢字、白話字、台羅佮閩拼(Hokkien Input Schema for Rime, including Chinese character, POJ, TL and BP),還支持普通話查詢、English 查詢等。
Hokkien Converter - Transliterate Hokkien to various romanization schemes online, powered by taibun.
[Mirror] Splits zh_TW/zh_CN input, looks up each part in Hokkien dictionary, then merges dict entries and original input back to a Mandarin -> Hokkien translation prompt - LLMs without Hokkien knowledge can learn from the prompt and give a decent translation
Mac OS X keyboard layout for Pe̍h-ōe-jī and related romanization systems
Add a description, image, and links to the hokkien topic page so that developers can more easily learn about it.
To associate your repository with the hokkien topic, visit your repo's landing page and select "manage topics."