---
language:
- en
- vi

tags:
- translation

license: apache-2.0
---

# MarianMT exported to the ONNX format

## Install Optimum
```bash
pip install optimum
```

## Usage example

```python
from transformers import AutoTokenizer
from optimum.onnxruntime import ORTModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("icon-it-tdtu/mt-en-vi-optimum")
model = ORTModelForSeq2SeqLM.from_pretrained("icon-it-tdtu/mt-en-vi-optimum")

text = "I am a student."
inputs = tokenizer(text, return_tensors='pt')
outputs = model.generate(**inputs)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
# Tôi là một sinh viên.
```