---
language: en
tags:
- token-classification
- ner
- transformers
license: apache-2.0
datasets:
- custom-dataset
metrics:
- precision
- recall
- f1
model_name: osa-custom-ner-model
widget:
- text: "The SALES of BEER and WINE in TTL US is increasing."
---

# My Custom NER Model

This is a custom **Named Entity Recognition (NER)** model fine-tuned on domain-specific data using a **BERT-based architecture**.

## Entities
The model is trained to recognize the following entities:
- **`FACT`**: Facts related to sales, revenue, etc.
- **`PRDC_CHAR`**: Product characteristics like product names.
- **`MRKT_CHAR`**: Market details like regions.

---

## Example Usage

```python
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline

# Load the model and tokenizer
model = AutoModelForTokenClassification.from_pretrained("AnanthanarayananSeetharaman/osa-custom-ner-model")
tokenizer = AutoTokenizer.from_pretrained("AnanthanarayananSeetharaman/osa-custom-ner-model")

# Create a pipeline
ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer)

# Test the pipeline
text = "The SALES of BEER and WINE in TTL US is increasing."
entities = ner_pipeline(text)
print(entities)