Repolode
投稿する
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.

GitHub で見る
スター
480
フォーク
59
未解決の Issue
16
最終コミット
12 か月前

これは何？

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.

主な機能

  • 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.

ユースケース

  • 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.

トピック

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

よくある質問

livecc とは？
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.
livecc は無料で使えますか？ライセンスは？
livecc にはライセンスが明記されていません。コードは公開されていますが、ライセンスがない場合は再利用の許諾がないため、利用前に作者に確認することをおすすめします。
livecc は今もメンテナンスされていますか？
半年以上コミットなし。livecc の最終コミットは 2025年10月29日 です。
livecc は何に使えますか？
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.
livecc はどこで入手できますか？
ソースコードとインストール手順は GitHub にあります：https://github.com/showlab/livecc

概要はプロジェクトの README をもとに AI が生成しています。GitHub の数値は毎日更新されます。

関連プロジェクト