Talk · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications · August 7, 2025
Deploying Multilingual ASR in Digital Twin Systems: A Performance and Efficiency Analysis of Whisper and SeamlessM4T
Bauyrzhan Amirkhanov, Gulnur Tyulepberdinova, Gulshat A. Amirkhanova, Sholpan Tletay, Alikhan Amirkhanov, Alina Raeva
Abstract
This study presents a systematic comparison of two leading automatic speech recognition (ASR) model families—OpenAI's Whisper and Meta's SeamlessM4T—across three typologically diverse languages: English (Germanic), Russian (Slavic), and Kazakh (Turkic). Motivated by the need to identify optimal ASR solutions for multilingual collaborative environments in digital twin development, we evaluate these models using standardized benchmarks including LibriSpeech and Common Voice datasets. Our analysis employs Word Error Rate (WER), Character Error Rate (CER), and GPU memory utilization as primary metrics. Results demonstrate that Whisper large-v3 achieves the best performance for English and Russian with WERs of 3.29% and 9.83% respectively, while SeamlessM4T-v2-large offers superior performance for Kazakh with a WER of 13.7%. GPU memory requirements range from 144.4MB to 6025.7MB, scaling with model size. These findings provide valuable guidance for selecting appropriate ASR models for multilingual applications in collaborative environments where accurate voice transcription is essential for human-machine interfaces in digital twin systems.
More by Alina Raeva
- Integration of a Photovoltaic Subsystem and a Digital Twin in the Power Supply System of Bakery ProductionInternational Conference on Nuclear and Renewable Energy Resources · 2026
- A hierarchical architecture for brownfield digitization: design, analytical insights, and validation of an ultra-low-cost Wi-Fi/MQTT IIoT frameworkFrontiers in Communications and Networks · 2026
- Hash-anchored quality-control evidence for food-production digital twins: a Solana-based LIMS-compatible frameworkFrontiers in Food Science and Technology · 2026
- Comprehensive techno-economic and empirical analysis of LoRaWAN infrastructure in high-density industrial environmentsInternational Conference on Advanced Sensing and Intelligent Systems · 2026
