---
language: en
pipeline_tag: token-classification
library_name: spacy
---

# NER Model: fuzzyethic/NER-ONETONOTE5

This is a Named Entity Recognition (NER) model, trained using spaCy.

## Model Details

*   **Language:** English (`en`)
*   **Pipeline:** `ner`
*   **spaCy Version:** >=3.8.7,<3.9.0

## Training

*   **Dataset:** This model was trained on the `ontonotes-5` dataset.
*   **Evaluation:** The model achieved an accuracy of **81%** on the evaluation set.

## How to Use

First, install the required libraries:
```bash
pip install spacy huggingface_hub
```

Then, you can use this script to automatically download and load the model:

```python
import spacy
from huggingface_hub import snapshot_download
import os

model_name = "fuzzyethic/NER-ONETONOTE5"

try:
    nlp = spacy.load(model_name)
except OSError:
    print(f"Downloading model {model_name} from Hugging Face Hub...")
    model_path = snapshot_download(repo_id=model_name)
    nlp = spacy.load(model_path)

text = "Apple Company is looking at buying U.K. startup for $1 billion"
doc = nlp(text)

print("Entities found:")
for ent in doc.ents:
    print(f"- {ent.text} ({ent.label_})")
```

OUTPUT

```python
Downloading model fuzzyethic/NER-ONETONOTE5 from Hugging Face Hub...
Entities found:
- Apple (B-ORG)
- Company (I-ORG)
- U.K. (B-GPE)
- $ (B-MONEY)
- 1 (I-MONEY)
- billion (I-MONEY)
```

## Labels

The model predicts the following entities:
```python
labels = [
    "B-CARDINAL", "B-DATE", "B-EVENT", "B-FAC", "B-GPE", "B-LANGUAGE", "B-LAW",
    "B-LOC", "B-MONEY", "B-NORP", "B-ORDINAL", "B-ORG", "B-PERCENT", "B-PERSON",
    "B-PRODUCT", "B-QUANTITY", "B-TIME", "B-WORK_OF_ART", "I-CARDINAL", "I-DATE",
    "I-EVENT", "I-FAC", "I-GPE", "I-LANGUAGE", "I-LAW", "I-LOC", "I-MONEY", "I-NORP",
    "I-ORDINAL", "I-ORG", "I-PERCENT", "I-PERSON", "I-PRODUCT", "I-QUANTITY",
    "I-TIME", "I-WORK_OF_ART"
]
```