FunAudioLLM/FunCineForge
A unified dataset pipeline and MLLM-based model for zero-shot movie dubbing across diverse cinematic scenes.
Not currently ranked — collecting fresh signals.
star history
Fun-CineForge provides an end-to-end pipeline for constructing large-scale dubbing datasets and an MLLM-based model designed for video-to-speech dubbing in movie content. It generates high-quality dubbed audio that matches lip-sync, preserves timbre, and follows instructions across multiple scenes including monologue, narration, dialogue, and multi-speaker scenarios. The project includes the CineDub-CN dataset, a large-scale Chinese television dubbing dataset with rich annotations.
Frequently asked
- What is FunAudioLLM/FunCineForge?
- A unified dataset pipeline and MLLM-based model for zero-shot movie dubbing across diverse cinematic scenes.
- Is FunCineForge open source?
- Yes — FunAudioLLM/FunCineForge is open source, released under the Apache-2.0 license.
- What language is FunCineForge written in?
- FunAudioLLM/FunCineForge is primarily written in Python.
- How popular is FunCineForge?
- FunAudioLLM/FunCineForge has 435 stars on GitHub.
- Where can I find FunCineForge?
- FunAudioLLM/FunCineForge is on GitHub at https://github.com/FunAudioLLM/FunCineForge.