Request for Task Level 3 Training Data

[EnisBerk]

Hello,

I'm writing to inquire about the training data for the model, specifically for Task Level 3, which includes audio-based storytelling (Story) and speech audio co-reasoning (SAC) tasks.

In your review responses, you mentioned that "We will release our source and training data to provide all implementation details if the paper is accepted." I have been able to find the source code and some of the training data, but I'm having trouble locating the datasets for Task Level 3.

Could you please provide some guidance on where I might find these datasets, or if they are not yet available, could you provide an estimated timeline for when they might be released?

Thank you for your time and for your contributions to the field.

Best, Enis

[signal1234]

@EnisBerk Hi, Do you know , how to train the 3 stages ? Just train with each stage data one by one , or is there any other param to change in between?

[EnisBerk]

Hi @signal1234, I am not one of the authors, I would not know for sure. You can open a new issue if you like.

[signal1234]

Thanks @EnisBerk