search

DAMO-NLP-SG / VideoLLaMA2

VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Apache License 2.0
865 stars 60 forks source link

When will you realease the audio branch? #25

Open HarryHsing opened 4 months ago

HarryHsing commented 4 months ago

Thank you very much for your amazing work on video-llama 2!

I wonder when will you release the training, testing code, and the pretrained weights for the audio branch?

Thanks!

Best, Zhenghao

lixin4ever commented 4 months ago

Really appreciate your kind words. We will release the code and the weights of the audio-language branch once we have a stable version.

zhangliyun9120 commented 4 months ago

@lixin4ever Hello, when will you release audio branch weights, is there any schedule?

CserDu commented 3 months ago

@lixin4ever Hi, I want to ask this question too. When will you release audio branch weights?

XuecWu commented 3 months ago

@lixin4ever Hi, could you tell me the possible release schedule? Thanks a lot!

xinyifei99 commented 2 weeks ago

Thanks for your attention! You can switch to the audio_visual branch (https://github.com/DAMO-NLP-SG/VideoLLaMA2/tree/audio_visual) and clone the repository to train and inference the audio_visual branch.