Alkd/speaker-embedding-onnx

By Alkd · ↓ 0 · ♥ 0 · Updated 2026-03-07

What's in this repo

This page lists the files in Alkd/speaker-embedding-onnx, including model.onnx.

1 ONNX models (.onnx files)
3 files, including 1 .md, 1 .onnx
Last updated 2026-03-07

ONNX files

File	Size	Download
model.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

speaker-embedding-onnx

ONNX export of the ResNet34 backbone from pyannote/wespeaker-voxceleb-resnet34-LM.

Follows the official wespeaker/bin/export_onnx.py approach: fbank features are computed externally, only the backbone is in ONNX.

Inputs / Outputs

Name	Shape	Description
`input_features`	`(batch, T, 80)`	Kaldi fbank features (T is dynamic)
`embedding`	`(batch, 256)`	Speaker embedding vector

Fbank parameters (must match at inference)

kaldi.fbank(wav * 32768, num_mel_bins=80, frame_length=25, frame_shift=10, round_to_power_of_two=True, window_type="hamming", use_energy=False, snip_edges=True, dither=0.0, sample_frequency=16000)

Then subtract per-bin mean: feats -= feats.mean(axis=0).

Model info

onnx speaker-verification wespeaker pyannote license:cc-by-4.0 region:us

↓ 0 ♥ 0

Created: 2026-03-07

Updated: 2026-03-07

View on Hugging Face

Files (3)

.gitattributes

README.md

model.onnx ONNX

Related models

More models

No task type declared.