A demo of the DiarizationLM model (diarizers-community/DiarizationLM-Gemma-4-E4B-v1) finetuned from Gemma 4 E4B. In this demo, we run a 4-bit quantized GGUF model (Q4_K_M) on CPU.
To learn more about DiarizationLM, check our paper: https://arxiv.org/abs/2401.03506