Enhanced Cricket Commentary Using AI Vision and Multilingual Translation

This paper presents a novel approach to generating cricket commentary using AI vision and multilingual support. The system utilizes GPT-4 Vision to process short, audio-free cricket videos as input, analyzing frames in video to create detailed visual descriptions of the ongoing action. Based on these frame-by-frame descriptions, commentary is automatically generated using GPT-40 Mini, which ensures the commentary is structured and relevant. Gemma 2B, fine-tuned specifically for cricket commentary, is then used to translate this commentary into multiple Indian languages, ensuring accurate and culturally appropriate translations. Finally, Eleven Labs is integrated to provide natural-sounding text-to-speech synthesis, converting the translated text into clear, human-like commentary in the user’s preferred language. This project aims to enhance the accessibility of cricket commentary, making it available in multiple languages and offering an immersive experience for a wider audience.

Authors

Institutions

Publication Details

Published
2025-02-21
DOI
https://doi.org/10.1109/mpseciceta64837.2025.11118722
Primary Topic
Natural Language Processing Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Enhanced Cricket Commentary Using AI Vision and Multilingual Translation

Noorbasha Mahammed Sameer, Karanam Jayavardhan, Oviya Ramalakshmi Iyyappan
Natural Language Processing Techniques
article

Enhanced Cricket Commentary Using AI Vision and Multilingual Translation

Noorbasha Mahammed Sameer, Karanam Jayavardhan, Oviya Ramalakshmi Iyyappan
article en

Abstract

This paper presents a novel approach to generating cricket commentary using AI vision and multilingual support. The system utilizes GPT-4 Vision to process short, audio-free cricket videos as input, analyzing frames in video to create detailed visual descriptions of the ongoing action. Based on these frame-by-frame descriptions, commentary is automatically generated using GPT-40 Mini, which ensures the commentary is structured and relevant. Gemma 2B, fine-tuned specifically for cricket commentary, is then used to translate this commentary into multiple Indian languages, ensuring accurate and culturally appropriate translations. Finally, Eleven Labs is integrated to provide natural-sounding text-to-speech synthesis, converting the translated text into clear, human-like commentary in the user’s preferred language. This project aims to enhance the accessibility of cricket commentary, making it available in multiple languages and offering an immersive experience for a wider audience.

Amrita Vishwa Vidyapeetham (IN)
Quality Education
Openalex Percentile: Top 89%
Natural Language Processing Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.