Ferramenta em Python para restauração cega de rostos, que melhora rostos borrados, de baixa qualidade ou danificados em fotos e vídeos usando um transformer com consulta a codebook.
18,2 mil3,7 milPythonOtherAtualizado há 11 meses
showlab/livecc
A video LLM trained with streaming speech transcription that produces real-time commentary on live video, from the CVPR 2025 LiveCC paper.
- Estrelas
- 480
- Forks
- 59
- Issues abertas
- 16
- Último commit
- há 12 meses
O que é?
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.
Recursos principais
- 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.
Casos de uso
- 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.
Tópicos
Perguntas frequentes
- O que é livecc?
- 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 é gratuito? Qual é a licença?
- livecc não declara licença. O código é público, mas sem licença você não tem permissão explícita para reutilizá-lo; fale com o autor antes de depender dele.
- livecc ainda é mantido?
- Sem commits há mais de 6 meses. O último commit de livecc foi em 29 de out. de 2025.
- Para que posso usar livecc?
- 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.
- Onde consigo livecc?
- O código-fonte e as instruções de instalação estão no GitHub: https://github.com/showlab/livecc
Resumo gerado por IA a partir do README do projeto. As estatísticas do GitHub são atualizadas diariamente.
Projetos relacionados
Open-source Python OCR library that detects and recognizes text in PDFs and images using deep learning models, built on PyTorch.
6,4 mil687PythonApache-2.0Atualizado há 4 horas
NEO is a family of native vision-language models that process pixels and words in one encoder-free dense architecture, with training and evaluation code.
90433PythonApache-2.0Atualizado há 3 meses
A PyTorch-based open-source framework for deep learning on healthcare imaging data, covering preprocessing, networks, losses and evaluation metrics.
8,8 mil1,7 milPythonApache-2.0Atualizado há 13 horas
Lightweight zipvoice-based TTS model for voice cloning and 48kHz speech generation, running at over 150x realtime on GPU.
5,5 mil685PythonApache-2.0Atualizado há 5 meses
A C++ video analysis framework that chains stream reading, model inference, tracking and output as pluggable pipeline nodes.
3 mil470C++Apache-2.0Atualizado há 8 meses