Migrate model card from transformers-repo
Browse filesRead announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/kuppuluri/telugu_bertu_ner/README.md
README.md
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Named Entity Recognition Model for Telugu
|
2 |
+
|
3 |
+
#### How to use
|
4 |
+
|
5 |
+
```python
|
6 |
+
from simpletransformers.ner import NERModel
|
7 |
+
model = NERModel('bert',
|
8 |
+
'kuppuluri/telugu_bertu_ner',
|
9 |
+
labels=[
|
10 |
+
'B-PERSON', 'I-ORG', 'B-ORG', 'I-LOC', 'B-MISC',
|
11 |
+
'I-MISC', 'I-PERSON', 'B-LOC', 'O'
|
12 |
+
],
|
13 |
+
use_cuda=False,
|
14 |
+
args={"use_multiprocessing": False})
|
15 |
+
|
16 |
+
text = "విరాట్ కోహ్లీ కూడా అదే నిర్లక్ష్యాన్ని ప్రదర్శించి కేవలం ఒక పరుగుకే రనౌటై పెవిలియన్ చేరాడు ."
|
17 |
+
results = model.predict([text])
|
18 |
+
```
|
19 |
+
|
20 |
+
## Training data
|
21 |
+
|
22 |
+
Training data is from https://github.com/anikethjr/NER_Telugu
|
23 |
+
|
24 |
+
## Eval results
|
25 |
+
|
26 |
+
On the test set my results were
|
27 |
+
|
28 |
+
eval_loss = 0.0004407190410447974
|
29 |
+
|
30 |
+
f1_score = 0.999519076627124
|
31 |
+
|
32 |
+
precision = 0.9994389677005691
|
33 |
+
|
34 |
+
recall = 0.9995991983967936
|
35 |
+
|