Skip to content

diar_sortformer_4spk-v1-fp16

mlx-community/diar_sortformer_4spk-v1-fp16
fp16 Open on Hugging Face
Parameters
124M
Weights (est.)
≈ 247 MB
Mac memory (est.)
8 GB+

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Details

Base model
nvidia/diar_sortformer_4spk-v1 (finetune)
Vendor
NVIDIA
Task
Voice activity detection
Quantisation
fp16
Licence
—
Downloads
100 in the last 30 days · 828 all time · 0 likes
Published
2026-02-10 · updated 2026-02-10 (9mo ago)
Tags
mlx-audio, sortformer, speaker-diarization, speech

Other MLX builds of nvidia/diar_sortformer_4spk-v1

Build Quantisation Weights Mac memory Downloads
diar_sortformer_4spk-v1-fp16 (this one) fp16 ≈ 247 MB 8 GB+ 100
diar_sortformer_4spk-v1-fp32 fp32 ≈ 494 MB 8 GB+ 127