Data used for training

[NielXUYitao]

Hi @xinformatics , may I ask if is it possible to upload the data used in Github as well? Thanks!

[xinformatics]

Hi @NielXUYitao, The training data, once converted to PyTorch tensors, becomes huge, and it is certainly not possible to upload them on GitHub. We have provided the locations of repositories from where we get the data and the embedding extractor code. Please visit the README of the project.