You can deploy this model and start earning money today!

Alkd/
speaker-embedding-onnx

Name: speaker-embedding-onnx
Availability: InStock

Views

No views yet

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).

Alkd/speaker-embedding-onnx

speaker-embedding-onnx

Inputs / Outputs

Fbank parameters (must match at inference)

Alkd/
speaker-embedding-onnx