Helsinki-NLP

/

opus-mt-en-zh

like 322

Follow

Language Technology Research Group at the University of Helsinki 213

Check this link: https://huggingface.co/docs/transformers/model_doc/marian

from transformers import MarianMTModel, MarianTokenizer

src_text = [
'Hello, Good to see you.',
 "It's a beautiful day!", 
'Good moods are the most important.',
]

model_name = "Helsinki-NLP/opus-mt-en-zh"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))
res = [tokenizer.decode(t, skip_special_tokens=True) for t in translated]
print(res)

the result is:

['你好,很高兴见到你。', '这是一个美丽的一天!', '良好的情绪是最重要的。']

tokenizer = AutoTokenizer.from_pretrained("Helsinki-NLP/opus-mt-en-zh")
model = AutoModelWithLMHead.from_pretrained("Helsinki-NLP/opus-mt-en-zh")
translation = pipeline("translation_en_to_zh", model=model, tokenizer=tokenizer)
#translation = pipeline("translation", model="Helsinki-NLP/opus-mt-en-zh")

text = "hello"
result = translation(text, max_length=40)[0]["translation_text"]
result is 哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈哈

transformers 4.31.0

I have also encountered this problem Have you solved it?