KevinAHM/soprano-onnx

By KevinAHM · ↓ 6 · ♥ 3 · Updated 2026-01-03

What's in this repo

This page lists the files in KevinAHM/soprano-onnx, including soprano_backbone_kv.onnx, soprano_decoder.onnx.

2 ONNX models (.onnx files)
11 files, including 5 .json, 2 .onnx, 1 .md, 1 .data
Last updated 2026-01-03

ONNX files

File	Size	Download
onnx/soprano_backbone_kv.onnx	—	Download
onnx/soprano_decoder.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

Soprano ONNX (KV Cache)

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

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

Model info

onnx qwen3 base_model:ekwek/Soprano-80M base_model:quantized:ekwek/Soprano-80M license:apache-2.0 region:us

↓ 6 ♥ 3

Created: 2026-01-03

Updated: 2026-01-03

View on Hugging Face

Files (11)

.gitattributes

LICENSE

README.md

config.json

generation_config.json

onnx/soprano_backbone_kv.onnx ONNX

onnx/soprano_decoder.onnx ONNX

onnx/soprano_decoder.onnx.data

special_tokens_map.json

tokenizer.json

tokenizer_config.json

Related models

More models

No task type declared.