Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems
Tuan Nguyen, Long-Vu Hoang, Huy-Dat Tran
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.
Related Papers
Visual-Language Model Knowledge Distillation Method for Image Quality Assessment2025-07-21Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine2025-07-17NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech2025-07-17Making Language Model a Hierarchical Classifier and Generator2025-07-17VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning2025-07-17The Generative Energy Arena (GEA): Incorporating Energy Awareness in Large Language Model (LLM) Human Evaluations2025-07-17Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities2025-07-17Assay2Mol: large language model-based drug design using BioAssay context2025-07-16