Update README.md
Browse files
README.md
CHANGED
@@ -1,10 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
-
title: README
|
3 |
-
emoji: 🐨
|
4 |
-
colorFrom: purple
|
5 |
-
colorTo: purple
|
6 |
-
sdk: static
|
7 |
-
pinned: false
|
8 |
-
---
|
9 |
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# 🌊 TinyWave: Compact & Expressive Speech Language Models
|
2 |
+
|
3 |
+
**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 speech–text generation**, optimized for real-time use on **commodity hardware**.
|
4 |
+
|
5 |
+
Built through **layer-aligned knowledge distillation**, TinyWave models retain **93–97%** of their teacher’s performance while using only **⅓ of the parameters** — ideal for use in voice agents, assistive technologies, and edge devices.
|
6 |
+
|
7 |
+
> 📖 Read the paper: [Efficient Interleaved Speech Modeling through Knowledge Distillation (arXiv:2506.23670)](https://arxiv.org/abs/2506.23670)
|
8 |
+
> 🌐 Demo & samples: [tinywave-landing](https://mohammadmahdinoori.github.io/tinywave-landing/)
|
9 |
+
> 💻 Code: [github.com/mohammadmahdinoori/TinyWave](https://github.com/mohammadmahdinoori/TinyWave)
|
10 |
+
|
11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
|
13 |
+
## 🔧 Model Variants
|
14 |
+
|
15 |
+
| Model | Modality | Tokenizer | Description |
|
16 |
+
|--------------------------------------------------------------|---------------------------|------------------------|---------------------------------------------|
|
17 |
+
| [`tinywave/speech-base-2b`](https://huggingface.co/tinywave/speech-base-2b) | Speech → Speech | `spiritlm_base` | Base phonetic-only speech generation |
|
18 |
+
| [`tinywave/speech-expressive-2b`](https://huggingface.co/tinywave/speech-expressive-2b) | Speech → Expressive Speech | `spiritlm_expressive` | Includes pitch + style tokens |
|
19 |
+
| [`tinywave/interleaved-expressive-2b`](https://huggingface.co/tinywave/interleaved-expressive-2b) | Text ↔ Speech (interleaved) | `spiritlm_expressive` | Multimodal expressive generation |
|
20 |
+
| [`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 |
|