---
license: mit
base_model: Qwen/Qwen2-7B-Instruct
tags:
- speech-to-speech
- dialogue
- full-duplex
- asr
- tts
- llm
- qwen2
- vad-free
- micro-turn
language:
- en
pipeline_tag: text-generation
---

# DuplexCascade: Full-Duplex Speech-to-Speech Dialogue with VAD-Free Cascaded ASR-LLM-TTS Pipeline and Micro-Turn Optimization

This repository provides the model for **DuplexCascade**, a full-duplex speech-to-speech dialogue system built on a cascaded ASR-LLM-TTS pipeline with **VAD-free interaction** and **micro-turn optimization**.

The backbone large language model is [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct), which was further fine-tuned for our duplex dialogue setting.

## Paper

Our paper is available on arXiv:

**Paper:** https://arxiv.org/abs/2603.09180

## Inference Code

Please refer to our GitHub repository for inference and implementation details:

**GitHub:** https://github.com/sbintuitions/DuplexCascade

## Model Description

DuplexCascade is designed for full-duplex spoken dialogue, enabling more natural interaction through:

- A cascaded **ASR-LLM-TTS** pipeline
- **VAD-free** dialogue control
- **Micro-turn optimization** for smoother turn-taking behavior

This model is obtained by fine-tuning [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) for the full-duplex dialogue setting.

## Base Model

- **Base LLM:** [Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct)

## License

This model is released under the **MIT License**.