FunClip

FunClip is a fully open-source, locally deployed automated video clipping tool. It leverages Alibaba TONGYI speech lab's open-source FunASR Paraformer series models to perform speech recognition on videos, after which users can freely choose text segments or speakers from the recognition results and click the clip button to obtain the video clip corresponding to the selected segments.

The tool integrates Alibaba's open-source industrial-grade model Paraformer-Large, which can also accurately predict timestamps in an integrated manner. It incorporates the hotword customization feature of SeACo-Paraformer, allowing users to specify certain entity words, names, etc., as hotwords during the ASR process to enhance recognition results. It also integrates the CAM++ speaker recognition model, enabling users to use the auto-recognized speaker ID as the target for trimming, to clip segments from a specific speaker.

Functionalities are realized through Gradio interaction, offering simple installation and ease of use, and the tool can also be deployed on a server and accessed via a browser. FunClip supports multi-segment free clipping and automatically returns full video SRT subtitles and target segment SRT subtitles. It also supports LLM-assisted clipping, including routing through OrcaRouter, an OpenAI-compatible smart-routing gateway.

Model selection options include the default Paraformer for Chinese video clipping, the flagship Fun-ASR-Nano checkpoint, SenseVoice for multilingual ASR with emotion and audio event tags, MOSS for long-form ASR with anonymous speaker labels and timestamps, and the Paraformer English model for English video clipping.