# ๐ŸŒŠ TinyWave: Compact & Expressive Speech Language Models **TinyWave** is a family of **efficient 2B-parameter speech language models** distilled from the 7B SPIRIT-LM teacher. These models support **speech-to-speech** and **interleaved speechโ€“text generation**, optimized for real-time use on **commodity hardware**. Built through **layer-aligned knowledge distillation**, TinyWave models retain **93โ€“97%** of their teacherโ€™s performance while using only **โ…“ of the parameters** โ€” ideal for use in voice agents, assistive technologies, and edge devices. > ๐Ÿ“– Read the paper: [Efficient Interleaved Speech Modeling through Knowledge Distillation (arXiv:2506.23670)](https://arxiv.org/abs/2506.23670) > ๐ŸŒ Demo & samples: [tinywave-landing](https://mohammadmahdinoori.github.io/tinywave-landing/) > ๐Ÿ’ป Code: [github.com/mohammadmahdinoori/TinyWave](https://github.com/mohammadmahdinoori/TinyWave) --- ## ๐Ÿ”ง Model Variants | Model | Modality | Tokenizer | Description | |--------------------------------------------------------------|---------------------------|------------------------|---------------------------------------------| | [`tinywave/speech-base-2b`](https://huggingface.co/tinywave/speech-base-2b) | Speech โ†’ Speech | `spiritlm_base` | Base phonetic-only speech generation | | [`tinywave/speech-expressive-2b`](https://huggingface.co/tinywave/speech-expressive-2b) | Speech โ†’ Expressive Speech | `spiritlm_expressive` | Includes pitch + style tokens | | [`tinywave/interleaved-expressive-2b`](https://huggingface.co/tinywave/interleaved-expressive-2b) | Text โ†” Speech (interleaved) | `spiritlm_expressive` | Multimodal expressive generation | | [`tinywave/expressive-spirit-lm-interleaved-librilight`](https://huggingface.co/tinywave/expressive-spirit-lm-interleaved-librilight) | Teacher (7B, interleaved) | `spiritlm_expressive` | LoRA-corrected SPIRIT-LM for distillation |