Add AutoTokenizer support (trust_remote_code)
Browse files
README.md
CHANGED
|
@@ -33,6 +33,7 @@ pip install git+https://huggingface.co/Ethosoft/turk-tokenizer
|
|
| 33 |
|
| 34 |
## Quick Start
|
| 35 |
|
|
|
|
| 36 |
```python
|
| 37 |
from turk_tokenizer import TurkTokenizer
|
| 38 |
|
|
@@ -43,6 +44,22 @@ for t in tokens:
|
|
| 43 |
print(t["token"], t["token_type"], t["morph_pos"])
|
| 44 |
```
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
Output:
|
| 47 |
```
|
| 48 |
<uppercase_word> ROOT 0
|
|
|
|
| 33 |
|
| 34 |
## Quick Start
|
| 35 |
|
| 36 |
+
**Direct usage:**
|
| 37 |
```python
|
| 38 |
from turk_tokenizer import TurkTokenizer
|
| 39 |
|
|
|
|
| 44 |
print(t["token"], t["token_type"], t["morph_pos"])
|
| 45 |
```
|
| 46 |
|
| 47 |
+
**HuggingFace AutoTokenizer:**
|
| 48 |
+
```python
|
| 49 |
+
from transformers import AutoTokenizer
|
| 50 |
+
|
| 51 |
+
tok = AutoTokenizer.from_pretrained("Ethosoft/turk-tokenizer", trust_remote_code=True)
|
| 52 |
+
out = tok("İstanbul'da meeting'e katılamadım")
|
| 53 |
+
|
| 54 |
+
out["input_ids"] # hash-stable int IDs
|
| 55 |
+
out["attention_mask"] # [1, 1, 1, ...]
|
| 56 |
+
out["token_type_ids"] # 0=root, 1=suffix, 2=bpe, 3=punct, 4=num, 5=url/social
|
| 57 |
+
out["morphological_tokens"] # full morphological dicts
|
| 58 |
+
|
| 59 |
+
# Batch:
|
| 60 |
+
out = tok(["Türkçe metin.", "Another sentence."])
|
| 61 |
+
```
|
| 62 |
+
|
| 63 |
Output:
|
| 64 |
```
|
| 65 |
<uppercase_word> ROOT 0
|