Mbart Large 50 One To Many Mmt

🚀 mBART-50 one to many multilingual machine translation

This model is a fine - tuned checkpoint of mBART - large - 50, designed for multilingual machine translation, capable of translating English to 49 other languages.

🚀 Quick Start

This model is a fine - tuned checkpoint of [mBART - large - 50](https://huggingface.co/facebook/mbart - large - 50). mbart - large - 50 - one - to - many - mmt is fine - tuned for multilingual machine translation. It was introduced in Multilingual Translation with Extensible Multilingual Pretraining and Finetuning paper.

The model can translate English to other 49 languages mentioned below. To translate into a target language, the target language id is forced as the first generated token. To force the target language id as the first generated token, pass the forced_bos_token_id parameter to the generate method.

💻 Usage Examples

Basic Usage

from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
article_en = "The head of the United Nations says there is no military solution in Syria"
model = MBartForConditionalGeneration.from_pretrained("facebook/mbart-large-50-one-to-many-mmt")
tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50-one-to-many-mmt", src_lang="en_XX")

model_inputs = tokenizer(article_en, return_tensors="pt")

# translate from English to Hindi
generated_tokens = model.generate(
    **model_inputs,
    forced_bos_token_id=tokenizer.lang_code_to_id["hi_IN"]
)
tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
# => 'संयुक्त राष्ट्र के नेता कहते हैं कि सीरिया में कोई सैन्य समाधान नहीं है'

# translate from English to Chinese
generated_tokens = model.generate(
    **model_inputs,
    forced_bos_token_id=tokenizer.lang_code_to_id["zh_CN"]
)
tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
# => '联合国首脑说,叙利亚没有军事解决办法'

📚 Documentation

See the [model hub](https://huggingface.co/models?filter=mbart - 50) to look for more fine - tuned versions.

🔧 Technical Details

Languages covered

📄 License

BibTeX entry and citation info

@article{tang2020multilingual,
    title={Multilingual Translation with Extensible Multilingual Pretraining and Finetuning},
    author={Yuqing Tang and Chau Tran and Xian Li and Peng-Jen Chen and Naman Goyal and Vishrav Chaudhary and Jiatao Gu and Angela Fan},
    year={2020},
    eprint={2008.00401},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}