Downloads · 30 days
0
littlebearlabs/witness-redimnet2-b6-mlx
witness-redimnet2-b6-mlx is a machine learning model from littlebearlabs. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as mit.
ReDimNet2-B6-lm speaker embedder (192-d, raw-16kHz-waveform in), converted to MLX safetensors for witness's on-device speaker diarization.
Downloads · 30 days
0
Access
Public
Updated Jun 6, 2026
Parameters
12.7M
50.7 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors50.7 MB · 100%
From the Hugging Face model README
ReDimNet2-B6-lm speaker embedder (192-d, raw-16kHz-waveform in), converted to MLX safetensors for witness's on-device speaker diarization.
b6-vox2-lm.pt (vox2, lm).PalabraAI/redimnet2 (arXiv 2603.11841).model.safetensors — weights converted verbatim from the PyTorch state-dict
(num_batches_tracked dropped, f32) by
.research/diarization/gen_redimnet2_embed_fixture.py.NOTES.md, TENSOR_SHAPES.txt — the conversion reference + full tensor
shape manifest the MLX C++ loader keys on.192-d embedding, not L2-normalized by the model (the witness crate
L2-normalizes after). Parity vs the PyTorch reference is 1 − cos ≤ 5e-7.
Converted to MLX for witness, an
open-source Rust toolkit for on-device system capture on macOS. Generated by
.research/diarization/publish_weights.sh.