Downloads · 30 days
35
0% of all-time downloads
bengali_language_NER
Suchandra/bengali_language_NER
bengali_language_NER is a token classification model from Suchandra. Use it when you need labels on individual words, such as names. It is set up for transformers.
<h1Bengali Named Entity Recognition</h1 Fine-tuning bert-base-multilingual-cased on Wikiann dataset for performing NER on Bengali language.
All-time downloads
41.7K
Public
Parameters
177M
1.4 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin709 MB · 50%
Parameter types
How the weights are stored.
F32177M · 100%
Try a prompt
Datasets
Model card
From the Hugging Face model README
<h1>Bengali Named Entity Recognition</h1>
Fine-tuning bert-base-multilingual-cased on Wikiann dataset for performing NER on Bengali language.
<h1>Results</h1>
Label ID and its corresponding label name
| Label ID | Label Name |
|---|---|
| 0 | O |
| 1 | B-PER |
| 2 | I-PER |
| 3 | B-ORG |
| 4 | I-ORG |
| 5 | B-LOC |
| 6 | I-LOC |
| Name | Overall F1 | LOC F1 | ORG F1 | PER F1 |
|---|---|---|---|---|
| Train set | 0.997927 | 0.998246 | 0.996613 | 0.998769 |
| Validation set | 0.970187 | 0.969212 | 0.956831 | 0.982079 |
| Test set | 0.9673011 | 0.967120 | 0.963614 | 0.970938 |
Example
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("Suchandra/bengali_language_NER")
model = AutoModelForTokenClassification.from_pretrained("Suchandra/bengali_language_NER")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "মারভিন দি মারসিয়ান"
ner_results = nlp(example)
ner_results
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Languages
- bn
- Created
- Mar 2, 2022
- Updated
- Jun 5, 2023