Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,12 @@ You can use tokenizer as following
|
|
12 |
from transformers import AutoTokenizer
|
13 |
tokenizer = AutoTokenizer.from_pretrained('alayaran/bodo-roberta-base')
|
14 |
|
15 |
-
tokenizer('कौटि नख'राव दैनि कानेक्सन होबाय')
|
16 |
|
17 |
# {'input_ids': [310, 294, 313, 267, 503, 11, 268, 263, 277, 298, 287, 265, 267, 321, 263, 265, 272, 310, 273, 378, 295, 266, 271, 263, 269], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}
|
18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
12 |
from transformers import AutoTokenizer
|
13 |
tokenizer = AutoTokenizer.from_pretrained('alayaran/bodo-roberta-base')
|
14 |
|
15 |
+
t = tokenizer('कौटि नख'राव दैनि कानेक्सन होबाय')
|
16 |
|
17 |
# {'input_ids': [310, 294, 313, 267, 503, 11, 268, 263, 277, 298, 287, 265, 267, 321, 263, 265, 272, 310, 273, 378, 295, 266, 271, 263, 269], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}
|
18 |
+
# to decode
|
19 |
+
|
20 |
+
tokenizer.decode(t['input_ids'],skip_special_tokens=True)
|
21 |
+
|
22 |
+
# "कौटि नख'राव दैनि कानेक्सन होबाय"
|
23 |
+
```
|