En Ko Transliterator

🚀 英文-韓文音譯模型

本項目提供了一個英文到韓文的音譯模型，能夠將英文單詞準確地音譯成韓文，為跨語言交流提供便利。

🚀 快速開始

以下是使用該模型進行英文到韓文音譯的示例代碼：

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

def transliteration(word: str):
    model_checkpoint = "eunsour/en-ko-transliterator"
    
    model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)
    tokenizer = AutoTokenizer.from_pretrained(model_checkpoint, src_lang="en", tgt_lang="ko")
    
    encoded_en = tokenizer(word, truncation=True, max_length=48, return_tensors="pt")
    generated_tokens = model.generate(**encoded_en)
    result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
    
    return result

transliteration("transformer")
# ['트랜스포머']

💻 使用示例

基礎用法

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

def transliteration(word: str):
    model_checkpoint = "eunsour/en-ko-transliterator"
    
    model = AutoModelForSeq2SeqLM.from_pretrained(model_checkpoint)
    tokenizer = AutoTokenizer.from_pretrained(model_checkpoint, src_lang="en", tgt_lang="ko")
    
    encoded_en = tokenizer(word, truncation=True, max_length=48, return_tensors="pt")
    generated_tokens = model.generate(**encoded_en)
    result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
    
    return result

transliteration("transformer")
# ['트랜스포머']

📄 許可證

本項目採用 Apache-2.0 許可證。