botdevringring/fr-naxai-ai-emotion-classification-081808122023(latest)
The model is trained on the emotion classification task in the French language. It uses 6 labels: anger, fear, joy love, sadness, surprise.
This model is finetuned from distilcamembert-base. A distillation version of the CamemBERT model, a RoBERTa French model version.
Model Details
- Language: fr
- Problem type: Multi-class Classification
- Model Architecture: CamemBERT
- Model Name: fr-naxai-ai-emotion-classification-081808122023
- Creation date:
Classification Report:
Label | Precision | Recall | f1-Score | Support |
---|---|---|---|---|
anger | 0.91 | 0.91 | 0.91 | 2824 |
fear | 0.89 | 0.87 | 0.88 | 2824 |
joy | 0.91 | 0.82 | 0.87 | 2824 |
love | 0.88 | 0.92 | 0.90 | 2824 |
sadness | 0.93 | 0.90 | 0.91 | 2823 |
surprise | 0.89 | 0.98 | 0.93 | 2824 |
How to use this model
You can use Python to access this model:
from transformers import pipeline
analyzer = pipeline(
task='text-classification',
model='botdevringring/fr-naxai-ai-emotion-classification-081808122023',
tokenizer='botdevringring/fr-naxai-ai-emotion-classification-081808122023'
)
result = analyzer(
"je commence à me sentir déprimé"
)
result
[
{
'label': 'sadness',
'score': 0.999739944934845
}
]
Or you can use cURL:
curl https://api-inference.huggingface.co/models/botdevringring/fr-naxai-ai-emotion-classification-081808122023 \
-X POST \
-d '{"inputs": "je commence à me sentir déprimé"}' \
-H 'Content-Type: application/json' \
-H "Authorization: Bearer <Your HF API token>"
Acknowledgements
Model trained by Eduardo Brigham for Naxai powered by The Ring Ring Company
- Downloads last month
- 952
Dataset used to train botdevringring/fr-naxai-ai-emotion-classification-081808122023
Evaluation results
- Accuracy on emotiontest set self-reported0.896
- Precision Macro on emotiontest set self-reported0.897
- Precision Micro on emotiontest set self-reported0.896
- Precision Weighted on emotiontest set self-reported0.897
- Recall Macro on emotiontest set self-reported0.896
- Recall Micro on emotiontest set self-reported0.896
- Recall Weighted on emotiontest set self-reported0.896
- F1 Macro on emotiontest set self-reported0.896
- F1 Micro on emotiontest set self-reported0.895
- F1 Weighted on emotiontest set self-reported0.895