Pyannote Segmentation 3.0 — MLX MLX compatible weights for pyannote/segmentation 3.0 (PyanNet), converted from the official PyTorch Lightning checkpoint with pre computed SincNet filters. Model PyanNet is a speaker segmentation model (~1.5M params) that processes 10 second audio windows and outputs 7 class powerset probabilities for up to 3 simultaneous speakers. Used for both voice activity detection (binary) and speaker diarization (per speaker). Architecture: SincNet → BiLSTM(4 layers) → Linear(2 layers) → 7 class softmax Output classes: non speech, spk1, spk2, spk3, spk1+2, spk1+3, spk2+3 Usage (Swift / MLX) Part of speech swift. Conversion Converts the gated pyannote/segmentation 3.0 checkpoint using a custom unpickler (no pyannote.audio dependency required). Key transformations: SincNet : pre compute 80 sinc bandpass filters (40 cos + 40 sin) from 40 learned (low hz, band hz) parameter pairs Conv1d : transpose weights [O, I, K] → [O, K, I] for MLX channels last BiLSTM : split into forward/backward stacks, sum bias ih + bias hh Linear/classifier : kept as is Weight Mapping PyTorch Key MLX Key Shape sincnet.conv1d.0.filterbank. (computed) sincnet.conv.0.weight [80, 251, 1] sinc…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy