This folder contains the pretrained models used for speaker identification and transcription. Because of size limitations, I cannot host all of them on Github. You have to download these models from the following sources. Make sure that the filenames match exactly.

from https://huggingface.co/ggerganov/whisper.cpp/tree/main ggml-large.bin (~ 3.1 GB) ggml-small.bin (~ 500 MB)