P

Pegasus Indonesian Base Finetune

Developed by thonyyy
This model is an Indonesian text summarization model based on the PEGASUS architecture, fine-tuned on the Indosum, Liputan6, and XLSum datasets, suitable for news text summarization tasks.
Downloads 172
Release Time : 6/27/2023

Model Overview

This is an automatic text summarization model specifically optimized for Indonesian text, with enhanced capabilities for processing news articles, enabling it to extract key information from lengthy texts to generate concise summaries.

Model Features

Multi-dataset Fine-tuning
Fine-tuned on three Indonesian datasets—Indosum, Liputan6, and XLSum—enhancing the model's generalization capabilities.
Integrated Text Preprocessing
Built-in text cleaning functionality that automatically handles distractions such as links and special characters.
TPU-Optimized Training
Trained using Google TPU Research Cloud to ensure an efficient training process.

Model Capabilities

Indonesian Text Summarization
News Content Refinement
Long Text Compression

Use Cases

News Media
News Summarization
Automatically generates concise summaries for news articles.
Achieved ROUGE-1 score of 52.43 on the Indosum dataset.
Content Analysis
Key Information Extraction from Reports
Extracts core content from lengthy reports.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase