T5 Translate En Ru Zh Base 200

🚀 T5 English, Russian and Chinese Multilingual Machine Translation

This model is a conventional T5 transformer in multitasking mode, precisely configured for machine translation between Russian, Chinese, and English. It can perform direct translation between any language pair with a simple prefix.

🚀 Quick Start

Prerequisites

This model requires the transformers library. You can install it using pip install transformers.

Basic Usage

The model can perform direct translation between any pair of Russian, Chinese, or English languages. For translation into the target language, specify the target language identifier as a prefix 'translate to :'. The source language may not be specified, and the source text may be multilingual.

💻 Usage Examples

Basic Usage

# Example of translating Russian to Chinese
from transformers import T5ForConditionalGeneration, T5Tokenizer

model_name = 'utrobinmv/t5_translate_en_ru_zh_small_1024'
model = T5ForConditionalGeneration.from_pretrained(model_name)
tokenizer = T5Tokenizer.from_pretrained(model_name)

prefix = 'translate to zh: '
src_text = prefix + "Цель разработки — предоставить пользователям личного синхронного переводчика."

# translate Russian to Chinese
input_ids = tokenizer(src_text, return_tensors="pt")

generated_tokens = model.generate(**input_ids)

result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
print(result)
#开发的目的是为用户提供个人同步翻译。

# Example of translating Chinese to Russian
from transformers import T5ForConditionalGeneration, T5Tokenizer

model_name = 'utrobinmv/t5_translate_en_ru_zh_small_1024'
model = T5ForConditionalGeneration.from_pretrained(model_name)
tokenizer = T5Tokenizer.from_pretrained(model_name)

prefix = 'translate to ru: '
src_text = prefix + "开发的目的是为用户提供个人同步翻译。"

# translate Chinese to Russian
input_ids = tokenizer(src_text, return_tensors="pt")

generated_tokens = model.generate(**input_ids)

result = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)
print(result)
#Цель разработки - предоставить пользователям персональный синхронный перевод.

✨ Features

• Supports direct translation between Russian, Chinese, and English.
• Multilingual source text is supported.
• Use a simple prefix to specify the target language.

📚 Documentation

Languages covered

Russian (ru_RU), Chinese (zh_CN), English (en_US)

Tags

• translation
• text2text-generation
• t5

License

apache-2.0

Datasets

• ccmatrix

Metrics

• sacrebleu

Model Index

📄 License

This project is licensed under the Apache-2.0 license.