Efficient Interleaved Speech Modeling through Knowledge Distillation
Abstract
TinyWave, a family of compact speech generation models, achieves high performance with minimal loss in quality by distilling large multimodal transformers, enabling real-time deployment in various applications.
Current speech language models exceed the size and latency constraints of many deployment environments. We build compact, expressive speech generation models through layer-aligned distillation, matching hidden states, attention maps, and softened logits to compress large multimodal transformers by 3x with minimal loss in performance. We introduce TinyWave, a family of 2B-parameter models for speech-to-speech and interleaved speech-text generation, trained on 50,000 hours of public audio. TinyWave supports (i) speech-only generation using phonetic or expressive tokens and (ii) mixed speech-text continuations. Evaluation on Libri-Light shows TinyWave within 1.4 normalized perplexity points of its teacher. Accuracy on spoken StoryCloze and SALMon reaches 93-97% of the teacher's performance, outperforming size-matched baselines. These models are optimized for deployment on commodity hardware, enabling applications in real-time conversational agents, assistive technologies, and low-resource environments. We release models, training code, and evaluation scripts to support reproducible research on compact, expressive speech generation.
Models citing this paper 6
Browse 6 models citing this paperDatasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper