aufklarer/WeSpeaker-ResNet34-LM-CoreML

WeSpeaker-ResNet34-LM — CoreML

CoreML conversion of WeSpeaker ResNet34-LM for Apple Neural Engine.

Produces 256-dimensional L2-normalized speaker embeddings from audio.

Model Details

Usage

let model = try await WeSpeakerModel.fromPretrained(backend: .coreML)
let embedding = model.embed(audio: samples, sampleRate: 16000)
let similarity = WeSpeakerModel.cosineSimilarity(embeddingA, embeddingB)

Variants

Links

• —Swift library: soniqo/speech-swift
• —Original model: pyannote/wespeaker-voxceleb-resnet34-LM

• —Guide: soniqo.audio/guides/embed-speaker
• —Docs: soniqo.audio
• —GitHub: soniqo/speech-swift