---
license: apache-2.0
datasets:
- FunAudioLLM/CineDub-Example
language:
- zh
- en
- fr
- es
- ja
- ko
- it
- ru
- de
tags:
- Dubbing
---

<p align="center">
<b>🎬 Fun-CineForge: A Unified Dataset Pipeline and Model for Zero-Shot Movie Dubbing<br>
in Diverse Cinematic Scenes</b>
</p>

<div align="center">

![license](https://img.shields.io/github/license/modelscope/modelscope.svg)
<a href=""><img src="https://img.shields.io/badge/OS-Linux-orange.svg"></a>
<a href=""><img src="https://img.shields.io/badge/Python->=3.8-aff.svg"></a>
<a href=""><img src="https://img.shields.io/badge/Pytorch->=2.1-blue"></a>
</div>

[Demos](https://funcineforge.github.io/); [Paper](https://arxiv.org/pdf/2601.14777); [Modelscope](https://www.modelscope.cn/models/FunAudioLLM/Fun-CineForge); [HuggingFace](https://huggingface.co/FunAudioLLM/Fun-CineForge)

**Fun-CineForge** contains an end-to-end dataset pipeline for producing large-scale dubbing datasets and an MLLM-based dubbing model designed for diverse cinematic scenes. Using this pipeline, we constructed the first large-scale Chinese television dubbing dataset CineDub-CN, which includes rich annotations and diverse scenes. In monologue, narration, dialogue, and multi-speaker scenes, our dubbing model consistently outperforms state-of-the-art methods in terms of audio quality, lip-sync, timbre transition, and instruction following.