使用模型Helsinki-NLP/opus-mt-en-zh实现英译中

hehui0921

已于 2024-02-13 13:53:08 修改

阅读量1.3k

点赞数 4

分类专栏： huggingface 文章标签：自然语言处理机器翻译人工智能

于 2024-02-13 13:21:28 首次发布

本文链接：https://blog.csdn.net/oHeHui1/article/details/136106485

版权

huggingface 专栏收录该内容

33 篇文章 0 订阅

订阅专栏

google codlab 运行需要5秒

from transformers import AutoModel , AutoTokenizer,MarianMTModel
from huggingface_hub.hf_api import HfFolder

HfFolder.save_token('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')

text ="Memphis is a series of models which advance human-data models, offering good performance without relying on proprietary model outputs"
mname ='Helsinki-NLP/opus-mt-en-zh'
tokenizer = AutoTokenizer.from_pretrained(mname)
model = MarianMTModel.from_pretrained(mname)
input_ids = tokenizer.encode(text, return_tensors="pt")
outputs = model.generate(input_ids)
decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(decoded)#Nice to meet you

也可以使用pipeline：

from transformers import AutoModel , AutoTokenizer,MarianMTModel
from transformers import pipeline

text ="Memphis is a series of models which advance human-data models, offering good performance without relying on proprietary model outputs"
mname ='Helsinki-NLP/opus-mt-en-zh'
translator = pipeline(model=mname)
print(translator(text)[0].get("generated_text"))