# T5-EN-VI-SMALL:Pretraining Text-To-Text Transfer Transformer for english vietnamese translation

## Results

The results test-2013-en-vi

| Model                                                                                                 | BLEU (Beam Search)
| ----------------------------------------------------------------------------------------------------- | ------------------
| [Luong & Manning (2015)](https://nlp.stanford.edu/pubs/luong-manning-iwslt15.pdf)                     | 23.30
| Sequence-to-sequence model with attention                                                             | 26.10
| Neural Phrase-based Machine Translation [Huang et. al. (2017)](https://arxiv.org/abs/1706.05565)      | 27.69
| Neural Phrase-based Machine Translation + LM [Huang et. al. (2017)](https://arxiv.org/abs/1706.05565) | 28.07
| t5-en-vi-small (pretraining)                                                                                 | **28.46** (cased)
| t5-en-vi-small (pretraining)                                                                                | **29.23** (uncased)

#### Example Using

``` bash
import torch

from transformers import MT5ForConditionalGeneration, T5Tokenizer
import torch
if torch.cuda.is_available():       
    device = torch.device("cuda")

    print('There are %d GPU(s) available.' % torch.cuda.device_count())

    print('We will use the GPU:', torch.cuda.get_device_name(0))
else:
    print('No GPU available, using the CPU instead.')
    device = torch.device("cpu")

model = MT5ForConditionalGeneration.from_pretrained("NlpHUST/t5-en-vi-small")
tokenizer = T5Tokenizer.from_pretrained("NlpHUST/t5-en-vi-small")
model.to(device)

src = "In school , we spent a lot of time studying the history of Kim Il-Sung , but we never learned much about the outside world , except that America , South Korea , Japan are the enemies ."
tokenized_text = tokenizer.encode(src, return_tensors="pt").to(device)
model.eval()
summary_ids = model.generate(
                    tokenized_text,
                    max_length=128, 
                    num_beams=5,
                    repetition_penalty=2.5, 
                    length_penalty=1.0, 
                    early_stopping=True
                )
output = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print(output)
```
#### Output

``` bash

Ở trường, chúng tôi dành nhiều thời gian để nghiên cứu về lịch sử Kim Il-Sung, nhưng chúng tôi chưa bao giờ học được nhiều về thế giới bên ngoài, ngoại trừ Mỹ, Hàn Quốc, Nhật Bản là kẻ thù.

```