Repolode
제출하기
showlab

showlab/livecc

A video LLM trained with streaming speech transcription that produces real-time commentary on live video, from the CVPR 2025 LiveCC paper.

GitHub에서 보기
스타
480
포크
59
열린 이슈
16
마지막 커밋
12개월 전

어떤 프로젝트인가요?

LiveCC is a video large language model trained on videos paired with streaming speech transcription, so it can generate running commentary while a video plays rather than only answering questions about a finished clip. The project is the research code for the CVPR 2025 paper of the same name, covering training, inference and evaluation.

The repository provides a Gradio web demo and a command-line demo for trying the model, along with pre-training and supervised fine-tuning scripts built on DeepSpeed and Hugging Face Transformers. Published checkpoints, datasets such as Live-WhisperX-526K, and a benchmark called LiveSports3KCC are linked from the README. Evaluation scripts cover VideoMME and OVOBench, and a data production pipeline is included for users who want to rebuild the training data.

The code targets Python 3.11 or newer and is built on Qwen2-VL-based models, with Flash Attention and Liger kernels used for efficiency.

핵심 기능

  • 01Generates real-time video commentary using streaming speech transcription training.
  • 02Includes a Gradio web demo and a command-line demo.
  • 03Provides pre-training and SFT scripts using DeepSpeed.
  • 04Ships evaluation scripts for LiveSports3KCC, VideoMME and OVOBench.
  • 05Links published checkpoints and training datasets on Hugging Face.

활용 사례

  • Researchers studying video LLMs trained on speech-aligned data.
  • Teams building live sports or event commentary prototypes.
  • Developers reproducing the LiveCC paper's training and evaluation results.

토픽

#video-llm#multimodal#speech-transcription#real-time#computer-vision#deep-learning#pytorch

자주 묻는 질문

livecc은(는) 무엇인가요?
A video LLM trained with streaming speech transcription that produces real-time commentary on live video, from the CVPR 2025 LiveCC paper. LiveCC is a video large language model trained on videos paired with streaming speech transcription, so it can generate running commentary while a video plays rather than only answering questions about a finished clip. The project is the research code for the CVPR 2025 paper of the same name, covering training, inference and evaluation.
livecc은(는) 무료로 사용할 수 있나요? 라이선스는 무엇인가요?
livecc에는 명시된 라이선스가 없습니다. 코드는 공개되어 있지만 라이선스가 없으면 재사용 허가가 명확하지 않으므로, 사용 전에 작성자에게 문의하는 것이 좋습니다.
livecc은(는) 아직 유지보수되고 있나요?
6개월 이상 커밋 없음. livecc의 마지막 커밋은 2025년 10월 29일입니다.
livecc은(는) 어디에 사용할 수 있나요?
Researchers studying video LLMs trained on speech-aligned data. Teams building live sports or event commentary prototypes. Developers reproducing the LiveCC paper's training and evaluation results.
livecc은(는) 어디서 받을 수 있나요?
소스 코드와 설치 방법은 GitHub에 있습니다: https://github.com/showlab/livecc

요약은 프로젝트 README를 바탕으로 AI가 작성했습니다. GitHub 통계는 매일 갱신됩니다.

관련 프로젝트