← Back to Projects

Hindi News Summarizer

SAR (सार) - State-of-the-art Summarization for Hindi

NLP BART T5 Hugging Face

Overview

SAR (सार) in Hindi means summary. This is my work on Hindi Text Summarization on news articles using state-of-the-art transformer models.

Hindi News Summarizer Interface

Models

Inference results are on 2k sample data:

Model Checkpoint Rouge-2 [f_score] Inference Time
BART ai4bharat/IndicBART 21.48 20min 27s
T5 csebuetnlp/mT5_multilingual_XLSum 20.21 45min 54s

API Usage

You can summarize any Hindi news article in just 5 lines of code:

import requests api_endpoint = "https://hf.space/embed/d0r1h/Hindi_News_Summarizer/+/api/predict/" news_url = "https://www.amarujala.com/uttar-pradesh/shamli/..." r = requests.post(url=api_endpoint, json={"data": [news_url, "BART"]}) print(r.json()['data'][0])