t5-base-indonesian-summarization-cased Open-source Summarization Model - Specialized for Indonesian Text Summarization Tasks

T5 Base Indonesian Summarization Cased

Developed by cahya

A T5-based summarization model optimized for Indonesian language, fine-tuned from huseinzol05's bahasa model, suitable for Indonesian text summarization tasks

Text Generation Other#Indonesian summarization #T5 base model #News text compression

Downloads 1,003

Release Time : 3/2/2022

Model Overview

This model is an Indonesian text summarization model based on the T5 architecture, fine-tuned on the Liputan6 news dataset, capable of generating high-quality Indonesian text summaries

Model Features

Indonesian language optimization

Specially optimized for Indonesian text characteristics, excelling in Indonesian summarization tasks

T5 architecture advantages

Based on the powerful T5 (text-to-text) architecture, unifying various NLP tasks

News domain adaptation

Fine-tuned using Indonesian news dataset (Liputan6), particularly suitable for news text summarization

Model Capabilities

Indonesian text summarization

Long text compression

Key information extraction

Use Cases

News media

Automatic news summarization

Generate concise summaries for Indonesian news articles

Can generate summaries within 80 words while retaining key information

Content analysis

Document key information extraction

Extract core content from long Indonesian documents

Effectively identifies document main ideas and key points

🚀 Indonesian T5 Summarization Base Model

This is a fine - tuned T5 base summarization model tailored for the Indonesian language, which effectively addresses the need for text summarization in Indonesian.

🚀 Quick Start

This model is a fine - tuned T5 base summarization model for Indonesian. It offers an efficient solution for summarizing Indonesian text.

✨ Features

Language - specific: Specifically designed for the Indonesian language.
Fine - tuned: Based on an existing model and fine - tuned with a relevant dataset.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import T5Tokenizer, T5Model, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("cahya/t5-base-indonesian-summarization-cased")
model = T5ForConditionalGeneration.from_pretrained("cahya/t5-base-indonesian-summarization-cased")

Advanced Usage

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("cahya/t5-base-indonesian-summarization-cased")
model = T5ForConditionalGeneration.from_pretrained("cahya/t5-base-indonesian-summarization-cased")

# 
ARTICLE_TO_SUMMARIZE = ""

# generate summary
input_ids = tokenizer.encode(ARTICLE_TO_SUMMARIZE, return_tensors='pt')
summary_ids = model.generate(input_ids,
            min_length=20,
            max_length=80,
            num_beams=10,
            repetition_penalty=2.5,
            length_penalty=1.0,
            early_stopping=True,
            no_repeat_ngram_size=2,
            use_cache=True,
            do_sample = True,
            temperature = 0.8,
            top_k = 50,
            top_p = 0.95)

summary_text = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
print(summary_text)

Output:

📚 Documentation

Finetuning Corpus

The t5 - base - indonesian - summarization - cased model is based on t5 - base - bahasa - summarization - cased by huseinzol05, and it is fine - tuned using the id_liputan6 dataset.

🔧 Technical Details

No technical details beyond the fine - tuning corpus are provided in the original document.

📄 License

No license information is provided in the original document.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご