adi-gov-tw/Taiwan-Tongues-ASR-CE
Taiwan Tongues ASR CE 是一個開源語音辨識（Automatic Speech Recognition, ASR）模型專案，專為台灣多元語言環境設計。 本模型支援 國語、台語、客語與英語，提供本地多語混合語音辨識，讓開發者與資訊服務業者可運用此開源模型進行 ASR 模型訓練、微調與發展在地化應用，以低成本、高效率進行 ASR 語音應用落地與智慧服務創新。 本專案為數位發展部數位產業署「114年數位產業跨域軟體基盤系統建置案」之實證成果之一，旨在推動台灣語音技術開源生態，協助資訊服務業者強化智慧應用能量，落實在地 AI 技術自主發展，由台灣大哥大執行與維護。
This project offers an Automatic Speech Recognition (ASR) service and models specifically designed for the diverse linguistic environment of Taiwan. It takes audio files or live speech in Mandarin, Taiwanese Hokkien, Hakka, and English, and outputs transcribed text. This is ideal for businesses and organizations that need to convert local multilingual audio into text for various applications.
Use this if you need to accurately convert spoken audio in Taiwan's common languages (Mandarin, Taiwanese Hokkien, Hakka, English) into text, either from existing audio files or in real-time.
Not ideal if your primary need is a simple, ready-to-use desktop application for transcription without any technical integration.
Stars
29
Forks
12
Language
Python
License
—
Category
Last pushed
Dec 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/adi-gov-tw/Taiwan-Tongues-ASR-CE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
YuanGongND/whisper-at
Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech...
huggingface/distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
phineas-pta/fine-tune-whisper-vi
jupyter notebooks to fine tune whisper models on Vietnamese using Colab and/or Kaggle and/or AWS EC2
KevKibe/African-Whisper
🚀 Framework for seamless fine-tuning of Whisper model on a multi-lingual dataset and deployment to prod.
huuquyet/PhoWhisper-next
Demo using PhoWhisper models of VinAI built with Transformers.js + Next.js