lakshaywadhwa1993
commited on
Commit
•
63ae242
1
Parent(s):
669b7d6
Model Card added
Browse files
README.md
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
Fine-tuning bert-base-multilingual-cased on Wikiann dataset for performing NER on Marathi language.
|
2 |
+
|
3 |
+
Label list: (0), B-PER (1), I-PER (2), B-ORG (3), I-ORG (4), B-LOC (5), I-LOC (6)
|
4 |
+
|
5 |
+
How to use the model:
|
6 |
+
from transformers import AutoTokenizer, AutoModelForTokenClassification
|
7 |
+
|
8 |
+
tokenizer = AutoTokenizer.from_pretrained("lakshaywadhwa1993/ner_marathi_bert")
|
9 |
+
|
10 |
+
model = AutoModelForTokenClassification.from_pretrained("lakshaywadhwa1993/ner_marathi_bert")
|
11 |
+
|
12 |
+
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
|
13 |
+
|
14 |
+
example = ["राज्यसभा","निवडणुकांसाठी","मुंबईत","भाजपचे" ,"चिंचवडचे", "आमदार", "लक्ष्मण", "जगताप"]
|
15 |
+
|
16 |
+
results = nlp(example)
|
17 |
+
|
18 |
+
results
|