pasha
commited on
Commit
·
f211e1f
1
Parent(s):
b820243
Readme updated
Browse files
README.md
CHANGED
@@ -1,3 +1,35 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
---
|
4 |
+
|
5 |
+
# morphemizer - Morpheme-based Russian Tokenizer
|
6 |
+
|
7 |
+
В репозитории содержится только токенизатор.
|
8 |
+
|
9 |
+
На данный момент проект на ранней стадии разработки.
|
10 |
+
|
11 |
+
## Как пользоваться
|
12 |
+
|
13 |
+
Для начала необходимо скачать пару библиотке:
|
14 |
+
|
15 |
+
```shell
|
16 |
+
pip install transformers rumorpheme
|
17 |
+
```
|
18 |
+
|
19 |
+
Небольшой пример использования:
|
20 |
+
|
21 |
+
```python
|
22 |
+
from transformers import AutoTokenizer
|
23 |
+
|
24 |
+
# Wrap it with RuMorphemeTokenizerFast for compatibility with transformers
|
25 |
+
tokenizer = AutoTokenizer.from_pretrained("./tokenizer", trust_remote_code=True)
|
26 |
+
|
27 |
+
test_text = "Философское восприятие мира."
|
28 |
+
# test_text = "Привет! Как твои дела?"
|
29 |
+
input_ids = tokenizer.encode(test_text)
|
30 |
+
|
31 |
+
print("Text:", test_text)
|
32 |
+
print("Encoded:", input_ids)
|
33 |
+
print("Tokens:", tokenizer.convert_ids_to_tokens(input_ids))
|
34 |
+
print("Decoded:", tokenizer.decode(input_ids))
|
35 |
+
```
|