Soprano ONNX (KV Cache)

This repository hosts ONNX exports of the Soprano 80M model with KV caching.

Contents

  • onnx/soprano_backbone_kv.onnx (backbone with past_key_values)
  • onnx/soprano_decoder.onnx + onnx/soprano_decoder.onnx.data (vocoder decoder)
  • / (tokenizer assets)

Inference & demo

See the streaming inference code here: https://github.com/KevinAHM/soprano-web-onnx

Not compatible with WebGPU via onnxruntime-web as of January 2026.

Upstream

Original project: https://github.com/ekwek1/soprano

Downloads last month
12
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for KevinAHM/soprano-onnx

Base model

ekwek/Soprano-80M
Quantized
(1)
this model

Collection including KevinAHM/soprano-onnx