| --- |
| language: |
| - vi |
| - ba |
| tags: |
| - translation |
| datasets: |
| - custom dataset |
| metrics: |
| - bleu |
| - sacrebleu |
| --- |
| # How to run the model |
| ```python |
| from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer |
| |
| model = M2M100ForConditionalGeneration.from_pretrained("transZ/M2M_Vi_Ba") |
| tokenizer = M2M100Tokenizer.from_pretrained("transZ/M2M_Vi_Ba") |
| tokenizer.src_lang = "vi" |
| vi_text = "Hôm nay ba đi chợ." |
| encoded_vi = tokenizer(vi_text, return_tensors="pt") |
| generated_tokens = model.generate(**encoded_vi, forced_bos_token_id=tokenizer.get_lang_id("ba")) |
| translate = tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0] |
| print(translate) |
| ``` |
