For the **test_all.csv**, it includes the test meta data for all three subtasks.

## Files
*   **train_clean.csv** - the meta data for clean training set
*   **train_noisy.csv** - the meta data for nosiy training set
*   **valid_clean.csv** - the meta data for clean validation set
*   **valid_noisy.csv** - the meta data for nosiy validation set
*   **test_all.csv** - the meta data for test set
*   **sample_submission.csv** - a sample submission file in the correct format
*   **images.zip** - a zip file containing all the raw images data retrieved from the video (25fps)
*   **audios.zip** - a zip file containing all the raw audio data retrieved from the video (16kHz)

If you are interested to process the raw video data or evaluating on the subtask mentioned on our paper, you can check our Github repo at: https://github.com/HLTCHKUST/CI-AVSR