Token Classification
Transformers
Safetensors
PyTorch
Baluchi
xlm-roberta
part-of-speech
pos-tagging
balochi
low-resource
universal-dependencies
shahbakhsh
Eval Results (legacy)
Instructions to use shahbakhsh/BalPOS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shahbakhsh/BalPOS with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="shahbakhsh/BalPOS")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("shahbakhsh/BalPOS") model = AutoModelForTokenClassification.from_pretrained("shahbakhsh/BalPOS", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| ,precision,recall,f1-score,support | |
| ADJ,0.785,0.8093,0.797,194.0 | |
| ADP,0.9517,0.9604,0.956,328.0 | |
| ADV,0.7556,0.7158,0.7351,95.0 | |
| AUX,0.9167,0.8919,0.9041,148.0 | |
| CCONJ,0.9434,1.0,0.9709,100.0 | |
| DET,0.8152,0.8065,0.8108,93.0 | |
| INTJ,0.0,0.0,0.0,1.0 | |
| NOUN,0.9198,0.8882,0.9037,671.0 | |
| NUM,0.7895,0.8824,0.8333,17.0 | |
| PART,0.8723,0.6508,0.7455,63.0 | |
| PRON,0.9101,0.9101,0.9101,178.0 | |
| PROPN,0.7681,0.8833,0.8217,60.0 | |
| PUNCT,0.9681,0.9945,0.9811,183.0 | |
| SCONJ,0.9219,0.9833,0.9516,60.0 | |
| VERB,0.84,0.9,0.869,210.0 | |
| X,0.0,0.0,0.0,0.0 | |
| accuracy,0.893,0.893,0.893,0.893 | |
| macro avg,0.7598,0.7673,0.7619,2401.0 | |
| weighted avg,0.8932,0.893,0.8922,2401.0 | |