This is a ResNet-152 speaker recognition model trained on the VoxBlink2 dataset, which contains 111,284 speakers.

The model is specifically adapted for telephone speech: the original data was downsampled to 8 kHz, and the GSM codec was applied to 50% of the data to simulate low-bandwidth conditions.

The backbone was trained using the WeSpeaker toolkit, following their standard VoxCeleb recipe.

If you use this model in your research, please cite the following paper: