FunClipIt is an AI automatic open source developed by Alibaba Damo Academy.Video Editing ToolsThe model performs speech recognition in the video, and then the user can freely select the text segment or speaker in the recognition result and click the crop button to obtain the corresponding segment of the video. This means that a lot of tedious work can be done by AI.
FunClip Features
Automated speech recognition: It integrates Alibaba's open source industrial-grade model Paraformer-Large, which is one of the open source Chinese ASR models with the best recognition effect. Modelscope has been downloaded more than 13 million times and can accurately predict timestamps in an integrated manner.
Hot word customization: Through the integrated SeACo-Paraformer model, users can specify some entity words, names, etc. as hot words to improve the recognition accuracy of specific words.
Speaker Recognition: Integrates the CAM++ speaker recognition model, allowing users to crop video segments of specific speakers based on automatically identified speaker IDs.
Video cropping: Users can select a text segment in the recognition result or specify a speaker and click the crop button to obtain the corresponding video segment.
Multi-segment editing support: FunClip supports users to perform multi-segment editing on videos, providing flexible editing capabilities.
Official website address:https://github.com/alibaba-damo-academy/FunClip