---
license: mpl-2.0
language:
- vi
- zh
pipeline_tag: translation
---

## How to run:

```python
import torch
import time
from transformers import AutoTokenizer, pipeline
from optimum.onnxruntime import ORTModelForSeq2SeqLM

model = ORTModelForSeq2SeqLM.from_pretrained("chi-vi/hirashiba-mt-tiny-zh-vi-onnx")
tokenizer = AutoTokenizer.from_pretrained("chi-vi/hirashiba-mt-tiny-zh-vi-onnx")

with open("test.txt") as f:
  text = f.readlines()

start_time = time.time()

pipe = pipeline("translation", model=model, tokenizer=tokenizer, device=0)
result = pipe(text)
print(result)

print("--- %s seconds ---" % (time.time() - start_time))
```