---
library_name: transformers
datasets:
- ShaomuTan/EC40
metrics:
- sacrebleu
pipeline_tag: translation
---

## Uses

```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline

model = AutoModelForSeq2SeqLM.from_pretrained('speedcell4/ec40-64k')
tokenizer = AutoTokenizer.from_pretrained('speedcell4/ec40-64k')

translation = pipeline(
    'translation', model=model, tokenizer=tokenizer,
    src_lang='<en>', tgt_lang='<ru>',
    max_length=256,
)

result, = translation(['The quick brown fox jumps over the lazy dog.'])
print(result['translation_text'])
# Быстрая коричневая лиса прыгает над ленивым собаком.
```