English

TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization

Sound 2025-09-03 v1 Artificial Intelligence Audio and Speech Processing

Abstract

The success of the generative model has gained unprecedented attention in the music generation area. Transformer-based architectures have set new benchmarks for model performance. However, their practical adoption is hindered by some critical challenges: the demand for massive computational resources and inference time, due to their large number of parameters. These obstacles make them infeasible to deploy on edge devices, such as smartphones and wearables, with limited computational resources. In this work, we present TinyMusician, a lightweight music generation model distilled from MusicGen (a State-of-the-art music generation model). TinyMusician integrates two innovations: (i) Stage-mixed Bidirectional and Skewed KL-Divergence and (ii) Adaptive Mixed-Precision Quantization. The experimental results demonstrate that TinyMusician retains 93% of the MusicGen-Small performance with 55% less model size. TinyMusician is the first mobile-deployable music generation model that eliminates cloud dependency while maintaining high audio fidelity and efficient resource usage

Keywords

Cite

@article{arxiv.2509.00914,
  title  = {TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization},
  author = {Hainan Wang and Mehdi Hosseinzadeh and Reza Rawassizadeh},
  journal= {arXiv preprint arXiv:2509.00914},
  year   = {2025}
}

Comments

12 pages for main context, 5 figures

R2 v1 2026-07-01T05:14:14.709Z