Intended uses & limitations
How to use
You can use this model with spacy.
!pip install https://huggingface.co/karthid/ta_Tamil_NER/resolve/main/ta_Tamil_NER-any-py3-none-any.whl
import ta_Tamil_NER
from spacy import displacy
nlp = ta_Tamil_NER.load()
doc = nlp("கூகுள் நிறுவனம் தனது முக்கிய வசதியான ஸ்ட்ரீட் வியூ வசதியை 10 நகரங்களில் இந்தியாவில் அறிமுகப்படுத்தி உள்ளது.")
displacy.render(doc,jupyter=True, style = "ent")
| Feature | Description |
|---|---|
| Name | ta_Tamil_NER |
| Version | 0.0.0 |
| spaCy | >=3.2.4,<3.3.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | Karthi Dhayalan |
Label Scheme
View label scheme
| Component | Labels |
|---|---|
ner |
B-PER, I-PER, B-ORG, I-ORG, B-LOC, I-LOC |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
84.92 |
ENTS_P |
84.34 |
ENTS_R |
85.52 |
TRANSFORMER_LOSS |
1842600.06 |
NER_LOSS |
108788.05 |
- Downloads last month
- -
Evaluation results
- NER Precisionself-reported0.843
- NER Recallself-reported0.855
- NER F Scoreself-reported0.849