Downloads · 30 days
6
3% of all-time downloads
fake-news-detector-es
jazska/fake-news-detector-es
fake-news-detector-es is a text classification model from jazska. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
You can explore the full source code, training scripts, and technical documentation in the following repository:
All-time downloads
199
Public
Parameters
178M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors711 MB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Oct 24, 2025
- Updated
- Oct 30, 2025
- SHA
- 395e53f5
Try a prompt
Base models
Model card
From the Hugging Face model README
GitHub Repository
You can explore the full source code, training scripts, and technical documentation in the following repository:
GitHub: jazska/fake-news-detector-es
Model Overview
This model is a Spanish-language fake news detector based on bert-base-multilingual-cased. It was fine-tuned on a custom dataset of real and fake news articles, combining titles and body text for contextual understanding.
The model performs binary text classification, predicting whether a news item is likely to be Real or Fake. It achieves high accuracy and balanced performance across precision, recall, and F1 score, making it suitable for public inference and deployment.
Key features:
- Language: Spanish 🇪🇸
- Task: Text Classification (Fake vs Real)
- Base model: BERT Multilingual
- Training framework: Hugging Face Transformers
- Evaluation metrics: Accuracy 95.47%, F1 Score 95.44%
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- es
- Created
- Oct 24, 2025
- Updated
- Oct 30, 2025