Bollyrics: Automatic Lyrics Generator for Romanised Hindi

TL;DR

This paper introduces Bollyrics, an automatic lyrics generator for romanized Hindi songs, addressing the lack of existing tools for Hindi lyrics generation and capturing rhyming patterns in the language.

Contribution

It presents a novel approach for generating Hindi song lyrics in romanized script, including techniques to incorporate rhyming patterns during training.

Findings

Developed a publicly available dataset and codebase.

Proposed simple techniques for rhyming pattern capture.

Demonstrated the effectiveness of the approach in Hindi lyric generation.

Abstract

Song lyrics convey a meaningful story in a creative manner with complex rhythmic patterns. Researchers have been successful in generating and analyisng lyrics for poetry and songs in English and Chinese. But there are no works which explore the Hindi language datasets. Given the popularity of Hindi songs across the world and the ambiguous nature of romanized Hindi script, we propose Bollyrics, an automatic lyric generator for romanized Hindi songs. We propose simple techniques to capture rhyming patterns before and during the model training process in Hindi language. The dataset and codes are available publicly at https://github.com/lingo-iitgn/Bollyrics.