|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- lao |
|
|
- vi |
|
|
metrics: |
|
|
- bleu |
|
|
pipeline_tag: translation |
|
|
--- |
|
|
|
|
|
## LaoVi-Translation |
|
|
|
|
|
Vietnamese-Lao and Lao-Vietnamese Translation models. |
|
|
|
|
|
- **Developed by:** Minggz |
|
|
|
|
|
|
|
|
## How to Use |
|
|
```python |
|
|
|
|
|
text = "ສະບາຍດີ, ຂ້ອຍເປັນວິສະວະກອນ NLP" |
|
|
laovi_model_dir = 'laovi_ctranslate2' |
|
|
#viru_model_dir = 'viru_ctranslate2' |
|
|
|
|
|
lao_tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = 'laovi_ctranslate2/source.model') |
|
|
vi_tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = 'laovi_ctranslate2/target.model') |
|
|
|
|
|
tokenized=lao_tokenizer.tokenize(text) |
|
|
|
|
|
translator = ctranslate2.Translator(laovi_model_dir) |
|
|
translated = translator.translate_batch([tokenized[0]]) |
|
|
print(vi_tokenizer.detokenize(translated[0][0]['tokens'])) |
|
|
|
|
|
|
|
|
|
