search

joonson / syncnet_trainer

Disentangled Speech Embeddings using Cross-Modal Self-Supervision
MIT License
155 stars 26 forks source link

makeFileList.py won't let any dev video out #15

Closed BehnazDibayee closed 3 years ago

BehnazDibayee commented 3 years ago

Hi,

I'm about to train the model with Voxceleb2 dataset just to monitor the train pipeline. I run this command on dev set: python ./makeFileList.py --output data/dev.txt --mp4_dir VOX2_PATH/dev/mp4 --txt_dir VOX2_PATH/dev/txt --wav_dir VOX2_PATH/dev/wav

But for all files I'm getting this error : Skipped ./vox2celeb/dev/mp4/id04484/ex2J3Oq2CAE/00084.mp4 - audio and video lengths different

I worth mentioning that I had extracted the .wav files from mp4 files by using ffmpeg instead of downloading audio files.

Could anyone help please?

BehnazDibayee commented 3 years ago

That was because of my ffmpeg version. It was too old (2.1.18)

I installed a new version and problem solved.

richardblythman commented 3 years ago

Hi @BehnazDibayee. What version of ffmpeg did you use? I am having the same issue using 2.8.17. Also, I extracted the .wav from the downloaded .aac files.