Address Ner Ru

🚀 address-ner-ru

An Address NER model designed to extract address components from strings.

https://huggingface.co/aidarmusin/address-ner-ru

🚀 Quick Start

The model can be used directly through the Hugging Face Transformers library. Here is a simple example of using the model:

from transformers import pipeline
import torch
import logging

device = "cuda:0" if torch.cuda.is_available() else "cpu"
logging.info(f"using device: {device}")

address_ner_pipeline = pipeline("ner", model="aidarmusin/address-ner-ru", device=device)

address = "628672,,,, Автономный Округ Ханты-Мансийский Автономный Округ - Югра,, Г. Лангепас, Ул. Солнечная, Д.21"
entities = address_ner_pipeline(address)
print(entities)

✨ Features

• This is an Address NER model that can accurately identify different parts of an address from a string.
• Trained on a dataset of 5K raw addresses, ensuring high accuracy and generalization ability.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import pipeline
import torch
import logging

device = "cuda:0" if torch.cuda.is_available() else "cpu"
logging.info(f"using device: {device}")

address_ner_pipeline = pipeline("ner", model="aidarmusin/address-ner-ru", device=device)

address = "628672,,,, Автономный Округ Ханты-Мансийский Автономный Округ - Югра,, Г. Лангепас, Ул. Солнечная, Д.21"
entities = address_ner_pipeline(address)
print(entities)

📚 Documentation

Dataset

The model is trained on a dataset of 5K raw addresses, with 90% of the data used for training and 10% for evaluation.

Evaluation

The model has been evaluated using multiple metrics, and the results are as follows:

📄 License

This project is licensed under the Apache-2.0 license.