|
--- |
|
language: |
|
- ru |
|
- bua |
|
- bxr |
|
datasets: |
|
- SaranaAbidueva/buryat-russian_parallel_corpus |
|
metrics: |
|
- bleu |
|
--- |
|
|
|
This model translates from Russian to Buryat language. |
|
|
|
|
|
How to use in Python: |
|
```python |
|
from transformers import MBartForConditionalGeneration, MBart50Tokenizer |
|
model = MBartForConditionalGeneration.from_pretrained("SaranaAbidueva/mbart50_ru_bua") |
|
tokenizer = MBart50Tokenizer.from_pretrained("SaranaAbidueva/mbart50_ru_bua") |
|
|
|
|
|
def translate(text, max_length=200, num_beams=5, repetition_penalty=5.0, **kwargs): |
|
encoded = tokenizer(text, return_tensors="pt") |
|
generated_tokens = model.generate( |
|
**encoded.to(model.device), |
|
max_length=max_length, |
|
num_beams=num_beams, |
|
repetition_penalty=repetition_penalty |
|
) |
|
return tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0] |
|
|
|
translate('Евгений Онегин интересная книга') |
|
``` |
