Distilbert Base Turkish Cased Emotion

🚀 distilbert-base-turkish-cased-emotion

This model is fine - tuned for text classification and emotion analysis on Turkish text, offering high - performance results.

🚀 Quick Start

This model, distilbert-base-turkish-cased-emotion, is a fine - tuned version of Distilbert-base-turkish-cased on the emotion dataset (translated to Turkish via Google Translate API). It uses HuggingFace Trainer with the following hyperparameters:

learning rate 2e-5, 
batch size 64,
num_train_epochs = 8,

✨ Features

• Tags: text - classification, emotion, pytorch
• Datasets: emotion (Translated to Turkish)
• Metrics: Accuracy, F1 Score

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import pipeline
classifier = pipeline("text-classification",
                       model='zafercavdar/distilbert-base-turkish-cased-emotion',
                       return_all_scores=True)
prediction = classifier("Bu kütüphaneyi seviyorum, en iyi yanı kolay kullanımı.", )
print(prediction)

"""
Output:
[
  [
    {'label': 'sadness', 'score': 0.0026786490343511105},
    {'label': 'joy', 'score': 0.6600754261016846},
    {'label': 'love', 'score': 0.3203163146972656},
    {'label': 'anger', 'score': 0.004358913749456406},
    {'label': 'fear', 'score': 0.002354539930820465},
    {'label': 'surprise', 'score': 0.010216088965535164}
  ]
]

"""

📚 Documentation

Model Performance Comparision on Emotion Dataset from Twitter

Dataset

The model is trained on the Twitter - Sentiment - Analysis dataset.

Eval results

{
 'eval_accuracy': 0.8325,
 'eval_f1': 0.8317301441160213,
 'eval_loss': 0.5021793842315674,
 'eval_runtime': 8.6167,
 'eval_samples_per_second': 232.108,
 'eval_steps_per_second': 3.714
}

📄 License

No license information is provided in the original document.