Update code
Browse files
README.md
CHANGED
@@ -52,6 +52,7 @@ The training dataset is based on [The Multilingual Amazon Reviews Corpus](https:
|
|
52 |
The model can be used as follows:
|
53 |
|
54 |
```python
|
|
|
55 |
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
56 |
|
57 |
tokenizer = AutoTokenizer.from_pretrained("msislam/code-mixed-language-detection-XLMRoberta")
|
@@ -60,14 +61,14 @@ model = AutoModelForTokenClassification.from_pretrained("msislam/code-mixed-lang
|
|
60 |
|
61 |
text = 'Hala Madrid y nada más. It means Go Madrid and nothing more.'
|
62 |
|
63 |
-
|
64 |
|
65 |
with torch.no_grad():
|
66 |
logits = model(**inputs).logits
|
67 |
|
68 |
labels_predicted = logits.argmax(-1)
|
69 |
|
70 |
-
lang_tag_predicted = [
|
71 |
lang_tag_predicted
|
72 |
```
|
73 |
|
|
|
52 |
The model can be used as follows:
|
53 |
|
54 |
```python
|
55 |
+
import torch
|
56 |
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
57 |
|
58 |
tokenizer = AutoTokenizer.from_pretrained("msislam/code-mixed-language-detection-XLMRoberta")
|
|
|
61 |
|
62 |
text = 'Hala Madrid y nada más. It means Go Madrid and nothing more.'
|
63 |
|
64 |
+
inputs = tokenizer(text, add_special_tokens= False, return_tensors="pt")
|
65 |
|
66 |
with torch.no_grad():
|
67 |
logits = model(**inputs).logits
|
68 |
|
69 |
labels_predicted = logits.argmax(-1)
|
70 |
|
71 |
+
lang_tag_predicted = [model.config.id2label[t.item()] for t in labels_predicted[0]]
|
72 |
lang_tag_predicted
|
73 |
```
|
74 |
|