I'm releasing the audio-visual diarization pipeline that was used to create the VoxConverse dataset. Along with the original code, an enhanced version featuring new VAD and speaker verification models is now available.

Since my PhD journey going towards the end (I’m currently looking for a full-time job in Research Engineer / Scientist positions!), I’m trying to open-source all the codes I’ve participated in! This is the first edition.

#VoxConverse #Speakerdiarization #Audiovisual