Update README.md
Browse files
README.md
CHANGED
@@ -6,4 +6,34 @@ language:
|
|
6 |
metrics:
|
7 |
- bleu
|
8 |
pipeline_tag: translation
|
9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
metrics:
|
7 |
- bleu
|
8 |
pipeline_tag: translation
|
9 |
+
---
|
10 |
+
|
11 |
+
## RuVi-Translation
|
12 |
+
|
13 |
+
### Model Description
|
14 |
+
|
15 |
+
Vietnamese-Russian and Russian-Vietnamese Translation models.
|
16 |
+
|
17 |
+
- **Developed by:** Minggz
|
18 |
+
|
19 |
+
|
20 |
+
## How to Use
|
21 |
+
```python
|
22 |
+
import ctranslate2
|
23 |
+
import pyonmttok
|
24 |
+
|
25 |
+
text = "Всем привет, я NLP-инженер"
|
26 |
+
ruvi_model_dir = 'ruvi_ctranslate2'
|
27 |
+
#viru_model_dir = 'viru_ctranslate2'
|
28 |
+
|
29 |
+
ru_tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = 'ru_spm.model')
|
30 |
+
vi_tokenizer=pyonmttok.Tokenizer(mode="none", sp_model_path = 'vi_spm.model')
|
31 |
+
|
32 |
+
tokenized=ru_tokenizer.tokenize(text)
|
33 |
+
|
34 |
+
translator = ctranslate2.Translator(ruvi_model_dir)
|
35 |
+
translated = translator.translate_batch([tokenized[0]])
|
36 |
+
print(vi_tokenizer.detokenize(translated[0][0]['tokens']))
|
37 |
+
```python
|
38 |
+
|
39 |
+
|