Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems

Tuan Nguyen, Long-Vu Hoang, Huy-Dat Tran
6/16/2025
cs.CLcs.SDeess.AS

No confident code implementation found for this paper.

Abstract

This paper presents our system for the MLC-SLM Challenge 2025, focusing on multilingual speech recognition and language modeling with large language models (LLMs). Our approach combines a fine-tuned Whisper-large-v3 encoder with efficient projector architectures and various decoder configurations. We employ a three-stage training methodology that progressively optimizes the encoder, projector, and LLM components. Our system achieves competitive performance with a private test average WER/CER result of 16.63% using the Gemma3-12B and 18.6% using the Qwen2.5-7B as decoder-only language model.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Transsion Multilingual Speech Recognition System for MLC-SLM 2025 Challenge

85% match2025

Bridging the gap: A comparative exploration of Speech-LLM and end-to-end architecture for multilingual conversational ASR

84% match2026

Triple X: A LLM-Based Multilingual Speech Recognition System for the INTERSPEECH2025 MLC-SLM Challenge

84% match2025

Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages

83% match2025

A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario

83% match2024

SHNU Multilingual Conversational Speech Recognition System for INTERSPEECH 2025 MLC-SLM Challenge

82% match2025

Cite this paper

@article{nguyen2025qwen,
  title  = {Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems},
  author = {Tuan Nguyen and Long-Vu Hoang and Huy-Dat Tran},
  year   = {2025},
  eprint = {2506.13596},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2506.13596v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2506.13596.svg)](https://codeofpaper.com/paper/2506.13596)

Discussion