chandassu 1.1.0

First-ever Python library implementing 'Chandassu', metrical poetry in Telugu Language (తెలుగు చంధస్సు)

Python library implementing "Chandassu", metrical poetry in Telugu Language (తెలుగు చంధస్సు).
arXiv Preprint: Read Here

Benchmarks

Performance evaluation across prosodic classes

Performance evaluation across padyam types

Our algorithm achieves 91.73% accuracy on the proposed Chandassu Score.

Usage

Install package using

pip install chandassu

Check padyam

from chandassu.laghuvu_guruvu import LaghuvuGuruvu
from chandassu.padya_bhedam import check_padyam

data= """తొండము నేక దంతమును తోరపు బొజ్జయు వామ హస్తమున్
మెండుగ మ్రోయు గజ్జెలును మెల్లని చూపులు మందహాసమున్
కొండొక గుజ్జు రూపమున కోరిన విద్యలకెల్ల నొజ్జవై
యుండెడి పార్వతీ తనయ యోయి గణాధిప నీకు మ్రొక్కెదన్"""

# Generate LaghuvuGuruvu Sequence
lg_data= LaghuvuGuruvu(data= data).generate()

score= check_padyam( 
                        lg_data= lg_data ,
                        type= "vutpalamaala",
                        return_micro_score= True, 
                        verbose= False
                    )

print(scores)

Computational Architecture

• nidhi.py: Telugu alphabet classification with phonological categorizations
  
• panimuttu.py: Vowel-consonant operations utility functions
  
• laghuvu_guruvu.py: Prosodic analysis engine with tokenizer and syllabic weight classifier
  
• ganam.py: Pattern repository mapping LaghuvuGuruvu sequences to metrical units
  
• padyam_config.py: Configuration database for padyam type constraints and rules
  
• check_lakshanam.py: Validation module for yati (caesura) and prasa (alliteration)
  
• padya_bhedam.py: Main integration module for metrical assessment and evaluation
  

Notebooks:

1. web_scrapping.ipynb: Scraper scripts to collect data from andhrabharati.com
2. Data_Analysis.ipynb: Analyzes data using different visualizations
3. Chandassu_Generation.ipynb: Generates chandassu for the scraped data
4. Score_Generation.ipynb: Computes scores by after chandassu generation
5. Accuracy_Evaluation.ipynb: Benchmarking and accuracy (Chandassu Score) evaluation

Eager to Contribute?

Any data, features, refactoring or your innovative thought, please check here.

Acknowledgements

Special thanks to Sesha Sai Vadapalli and Kalepu Nagabhushana Rao, maintainers of andhrabharati.com.
Appana Mohan Naga Phani Kumar for proofreading our article.
Sincere gratitude to our parents and family members for their continuous support throughout this work.
This work was undertaken with the grace of Sri Ramalinga Chowdeswari Devi.

Citation

@misc{pavan2025computationalsociallinguisticstelugu,
title={Computational Social Linguistics for Telugu Cultural Preservation: Novel Algorithms for Chandassu Metrical Pattern Recognition},
author={Boddu Sri Pavan and Boddu Swathi Sree},
year={2025},
eprint={2510.01233},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2510.01233},
}

Thank You !