adi-gov-tw/Taiwan-Tongues-ASR-CE-pretrained-v2.0

Taiwan-Tongues-ASR-CE-pretrained Model v2.0

Taiwan-Tongues-ASR-CE-pretrained-v2.0 是以 openai/whisper-large-v2 為基礎訓練的 Hugging Face Transformers 版本模型。此版本新增印尼文（Indonesian, id）語音辨識能力，並持續支援華語、台語、客語與英語。

這個 repository 提供 model.safetensors 與完整 tokenizer / processor 設定，適合用於 Transformers 推論、繼續訓練或微調。若需要 CTranslate2 / faster-whisper 推論版本，請使用 Taiwan-Tongues-ASR-CE-v2.0。

專案原始碼與訓練流程請見 Taiwan-Tongues-ASR-CE。

Version

Version	Base model	Format	Main update
v2.0	openai/whisper-large-v2	Transformers (model.safetensors)	Added Indonesian (id) support

Supported Languages

Language	Code
Mandarin Chinese	zh
Taiwanese Hokkien	nan
Hakka	hak
English	en
Indonesian	id

Files

This repository contains the Transformers checkpoint and tokenizer assets:

• model.safetensors
• config.json
• generation_config.json
• preprocessor_config.json
• tokenizer.json
• tokenizer_config.json
• vocab.json
• merges.txt
• normalizer.json
• added_tokens.json
• special_tokens_map.json

Usage

Install the required packages:

pip install torch transformers

Run automatic speech recognition with Transformers:

from transformers import pipeline

asr = pipeline(
    "automatic-speech-recognition",
    model="adi-gov-tw/Taiwan-Tongues-ASR-CE-pretrained-v2.0",
    device=0,
)

result = asr(
    "audio.wav",
    generate_kwargs={
        "language": "id",
        "task": "transcribe",
    },
)

print(result["text"])

Change language to zh, nan, hak, en, or id according to the input audio.

Notes

• This is the pretrained / Transformers model package.
• For faster production inference with CTranslate2 or faster-whisper, use Taiwan-Tongues-ASR-CE-v2.0.
• The license is listed as other; please refer to the project and release documentation before redistribution or commercial use.