Downloads · 30 days
13
21% of all-time downloads
soprano-onnx
KevinAHM/soprano-onnx
soprano-onnx is a machine learning model from KevinAHM. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository hosts ONNX exports of the Soprano 80M model with KV caching.
All-time downloads
63
Public
Repo size
378 MB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.onnx320 MB · 84%
At a glance
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jan 3, 2026
- Updated
- Jan 3, 2026
- SHA
- a5669835
Base models
Model card
From the Hugging Face model README
Soprano ONNX (KV Cache)
This repository hosts ONNX exports of the Soprano 80M model with KV caching.
Contents
onnx/soprano_backbone_kv.onnx(backbone withpast_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
- Type
- qwen3
- License
- apache-2.0
- Created
- Jan 3, 2026
- Updated
- Jan 3, 2026