Emotion Classifier - Aurora - islamamro
Classifies short text into emotions (joy, sadness, anger, fear, love, surprise).
Fine-tuned from distilbert-base-uncased on SetFit/emotion. Built, trained and published end-to-end via the Aurora Research Portal by islamamro on an NVIDIA RTX 3090.
- Task: text classification (6 classes)
- Held-out accuracy: 0.82
Use it
from transformers import pipeline
clf = pipeline("text-classification", model="Islamamro/emotion-aurora-islamamro")
clf("your text here")
Note
Trained on a 1,400-example demo subset - a proof of the Aurora build->train->publish pipeline, not a production model. Fine-tune on full data for real use.
- Downloads last month
- -