metadata
library_name: transformers
pipeline_tag: text-classification
language:
- ur
- multilingual
license: apache-2.0
tags:
- urdu
- roman-urdu
- xlm-roberta
- text-classification
- sentiment-analysis
- sentiment-classification
- social-media
socialsense-xmlr
Fine-tuned XLM-R for Urdu & Roman Urdu text sentiment classification.
Labels
- 0: NEGATIVE
- 1: NEUTRAL
- 2: POSITIVE
Usage
from transformers import pipeline
pipe = pipeline("text-classification",
model="yahyaqarni/socialsense-xmlr",
tokenizer="yahyaqarni/socialsense-xmlr",
top_k=None)
print(pipe("یہ بہت اچھا ہے"))
print(pipe("me bilkul khush nai hoon"))
Acknowledgements
This model was fine-tuned from cardiffnlp/twitter-xlm-roberta-base-sentiment, originally released under the Apache 2.0 License.