opus-mt-tc-big-en-tr

神经机器翻译模型，用于将英语（en）翻译为土耳其语（tr）。

该模型是 OPUS-MT project 的一部分，旨在使神经机器翻译模型在世界上众多语言中得以广泛使用和获取。所有模型最初使用 Marian NMT 的出色框架进行训练， Marian NMT 是一款使用纯C++编写的高效NMT实现。使用transformers库由huggingface将模型转换为pyTorch。训练数据来自 OPUS ，训练流程使用了 OPUS-MT-train 的程序。

• Publications: OPUS-MT – Building open translation services for the World 和 The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT （如果使用此模型，请引用。）

@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

• 发布日期：2022-02-25
• 源语言：eng
• 目标语言：tur
• 模型：transformer-big
• 数据：opusTCv20210807+bt（ source ）
• 标记化：SentencePiece（spm32k，spm32k）
• 原始模型： opusTCv20210807+bt_transformer-big_2022-02-25.zip
• 更多信息的发布模型： OPUS-MT eng-tur README

用法

一个简短的示例代码：

from transformers import MarianMTModel, MarianTokenizer

src_text = [
    "I know Tom didn't want to eat that.",
    "On Sundays, we would get up early and go fishing."
]

model_name = "pytorch-models/opus-mt-tc-big-en-tr"
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:
#     Tom'un bunu yemek istemediğini biliyorum.
#     Pazar günleri erkenden kalkıp balık tutmaya giderdik.

您还可以使用transformers的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-tr")
print(pipe("I know Tom didn't want to eat that."))

# expected output: Tom'un bunu yemek istemediğini biliyorum.

基准测试

• 测试集翻译结果： opusTCv20210807+bt_transformer-big_2022-02-25.test.txt
• 测试集分数： opusTCv20210807+bt_transformer-big_2022-02-25.eval.txt
• 基准测试结果：benchmark_results.txt
• 基准测试输出：benchmark_translations.zip

致谢

该工作得到 European Language Grid 的支持，作为 pilot project 2866 的一部分，通过欧洲研究理事会（ERC）在欧洲联盟的Horizon 2020研究和创新计划（授权协议号771113）下由 FoTran project 资助，以及 MeMAD project ，欧盟的Horizon 2020研究和创新计划根据授权协议号780069提供的资助。我们还感谢 CSC -- IT Center for Science 提供的慷慨计算资源和IT基础设施，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18:11:39 EEST
• 转换机器：LM0-400-22516.local