|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- accuracy |
|
|
- precision |
|
|
- recall |
|
|
- f1 |
|
|
pipeline_tag: token-classification |
|
|
tags: |
|
|
- ner |
|
|
- spacika_spacy |
|
|
- english |
|
|
- token classification |
|
|
--- |
|
|
|
|
|
.png) |
|
|
|
|
|
# 🛰️ Spacika — Custom Named Entity Recognition Model |
|
|
|
|
|
**Spacika** is a powerful and lightweight Named Entity Recognition (NER) model, fine-tuned to extract meaningful entities like names, organizations, locations, and more from natural language text. |
|
|
|
|
|
Created with precision and passion by **[Varnika](https://huggingface.co/Varnikasiva)**, Spacika blends the power of transformer-backed models with production-friendly NER pipeline. |
|
|
|
|
|
--- |
|
|
|
|
|
## ✨ Features |
|
|
|
|
|
- ✅ Fast and efficient NER tagging |
|
|
- 🧠 Transformer-based backbone |
|
|
- 📚 Trained on domain-specific and/or general English data |
|
|
- 🔖 Identifies entities like `PERSON`, `ORG`, `GPE`, `DATE`, `MONEY`, and more |
|
|
- 🌐 Easy to load, test, and integrate into any Python NLP workflow |
|
|
|
|
|
--- |
|
|
|
|
|
## 🤝 Collaborate with Me |
|
|
|
|
|
I'm open to collaborations, research projects, and ideas to extend this model or build similar applications. |
|
|
|
|
|
📬 **Email:** [varnikas753@gmail.com](mailto:varnikas753@gmail.com) |
|
|
|
|
|
|
