cheyneycomputerscience / crema-d Goto Github PK

Where is the download link? and What are the training and testing split settngs?

I cann't open those files
run ffmpeg -i CREMA-D-master/AudioWAV/1001_DFA_ANG_XX.wav test.wav
got CREMA-D-master/AudioWAV/1001_DFA_ANG_XX.wav: Invalid data found when processing input

Is it store somewhere the analytics per person, (age, gender etc)?

The file present inside AudioWAV folder is incorrectly named as 1040_ITH_SAD_X.wav. It must be named 1040_ITH_SAD_XX.wav as per the directions given in the README.md file.

For audio data, '1076_MTI_NEU_XX.mp3' and '1076_MTI_NEU_XX.wav' can't play, and '1076_MTI_SAD_XX.mp3' and '1076_MTI_SAD_XX.wav' can play but there is no sound.
For video data, '1076_MTI_NEU_XX.flv' has no sound, and '1076_MTI_SAD_XX.flv' has no face which looks like below.

Looking forward to the correct data!

After downloading with git-lfs, one obtains all the sound files but unfortunately, the video files are corrupted. They have an average size of 300 kb and can't be played.

Hi,
I am planning to use this dataset in my work. I am wondering if you have an evaluation protocol for the cross validation where you provide the information for the train, test, and validation sets?