# xzf-thu/Mini-Omni-Reasoner

<https://repo.masters-masters.com/en/repos/xzf-thu/Mini-Omni-Reasoner>

[Home](https://repo.masters-masters.com/en) › [xzf-thu](https://repo.masters-masters.com/en/owners/xzf-thu) › [Mini-Omni-Reasoner](https://repo.masters-masters.com/en/repos/xzf-thu/Mini-Omni-Reasoner)

xzf-thu/Mini-Omni-Reasoner has 171 stars on GitHub. Its RepoMasters card: Prototype tier. Mini-Omni-Reasoner: a real-time speech reasoning framework that…

| Field | Value |
| --- | --- |
| Owner | [xzf-thu](https://repo.masters-masters.com/en/owners/xzf-thu) |
| Stars | 171 |
| Forks | 19 |
| Language | No language |
| License | MIT |
| Created | 2025 |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [xzf-thu/Mini-Omni-Reasoner](https://github.com/xzf-thu/Mini-Omni-Reasoner) |

## Repository

Mini-Omni-Reasoner: a real-time speech reasoning framework that interleaves silent reasoning tokens with spoken response tokens (“thinking-in-speaking”), exploiting the LLM–audio throughput gap to keep speech fluent and low-latency while maintaining structured internal reasoning.

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

## More repos by xzf-thu

- [xzf-thu/VoiceMem · ★ 2,870 · Python · RC](https://repo.masters-masters.com/en/repos/xzf-thu/VoiceMem)
- [xzf-thu/Mega-ASR · ★ 1,148 · Python · Beta](https://repo.masters-masters.com/en/repos/xzf-thu/Mega-ASR)
- [xzf-thu/Audio-Interaction · ★ 591 · Python · Alpha](https://repo.masters-masters.com/en/repos/xzf-thu/Audio-Interaction)
- [xzf-thu/Audio-Reasoner · ★ 300 · Python · Alpha](https://repo.masters-masters.com/en/repos/xzf-thu/Audio-Reasoner)
- [xzf-thu/Pask · ★ 219 · Python · Prototype](https://repo.masters-masters.com/en/repos/xzf-thu/Pask)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.