英文

opus-mt-tc-big-en-it

神经机器翻译模型,用于将英语(en)翻译成意大利语(it)。

此模型是 OPUS-MT project 的一部分,该项目旨在使神经机器翻译模型普遍可用并可访问多种世界语言。所有模型最初是使用 Marian NMT 框架进行训练的,该框架是一个用纯C++编写的高效NMT实现。这些模型已经使用huggingface的transformers库将其转换为pyTorch。训练数据取自 OPUS ,训练流程使用 OPUS-MT-train 的程序。

@inproceedings{tiedemann-thottingal-2020-opus,
    title = "{OPUS}-{MT} {--} Building open translation services for the World",
    author = {Tiedemann, J{\"o}rg  and Thottingal, Santhosh},
    booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation",
    month = nov,
    year = "2020",
    address = "Lisboa, Portugal",
    publisher = "European Association for Machine Translation",
    url = "https://aclanthology.org/2020.eamt-1.61",
    pages = "479--480",
}

@inproceedings{tiedemann-2020-tatoeba,
    title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}",
    author = {Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the Fifth Conference on Machine Translation",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2020.wmt-1.139",
    pages = "1174--1182",
}

模型信息

使用方法

一个简短的示例代码:

from transformers import MarianMTModel, MarianTokenizer

src_text = [
    "He was always very respectful.",
    "This cat is black. Is the dog, too?"
]

model_name = "pytorch-models/opus-mt-tc-big-en-it"
tokenizer = MarianTokenizer.from_pretrained(model_name)
model = MarianMTModel.from_pretrained(model_name)
translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True))

for t in translated:
    print( tokenizer.decode(t, skip_special_tokens=True) )

# expected output:
#     Era sempre molto rispettoso.
#     Questo gatto e' nero, e' anche il cane?

您还可以使用transformers pipelines来使用OPUS-MT模型,例如:

from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-en-it")
print(pipe("He was always very respectful."))

# expected output: Era sempre molto rispettoso.

基准测试

langpair testset chr-F BLEU #sent #words
eng-ita tatoeba-test-v2021-08-07 0.72539 53.9 17320 116336
eng-ita flores101-devtest 0.59002 29.6 1012 27306
eng-ita newssyscomb2009 0.60759 31.2 502 11551
eng-ita newstest2009 0.60441 31.6 2525 63466

致谢

该工作得到 European Language Grid 的支持,作为 pilot project 2866 ,由 FoTran project 资助,资助机构为欧洲研究理事会(ERC)在欧洲联盟的Horizon 2020研究和创新计划下(授权协议编号为771113),以及 MeMAD project ,由欧洲联盟的Horizon 2020研究和创新计划在授权协议编号为780069下资助。我们还对 CSC -- IT Center for Science 提供的慷慨计算资源和IT基础设施表示感谢,芬兰。

模型转换信息

  • transformers版本:4.16.2
  • OPUS-MT git哈希:3405783
  • 转换时间:2022年4月13日17:27:22 EEST
  • 转换机器:LM0-400-22516.local