sheldonrobinson/Kroko-ASR
By sheldonrobinson · ↓ 0 · ♥ 0 · Updated 2025-08-23
What's in this repo
This page lists the files in sheldonrobinson/Kroko-ASR, including de_decoder.onnx, de_encoder.onnx, de_joiner.onnx and more.
- 12 ONNX models (.onnx files)
- 20 files, including 12 .onnx, 4 .txt, 1 .md, 1 .py
- Last updated 2025-08-23
ONNX files
| File | Size | Download |
|---|---|---|
| de/de_decoder.onnx | — | Download |
| de/de_encoder.onnx | — | Download |
| de/de_joiner.onnx | — | Download |
| en/en_decoder.onnx | — | Download |
| en/en_encoder.onnx | — | Download |
| en/en_joiner.onnx | — | Download |
| es/es_decoder.onnx | — | Download |
| es/es_encoder.onnx | — | Download |
| es/es_joiner.onnx | — | Download |
| fr/fr_decoder.onnx | — | Download |
Showing 10 of 12 .onnx files — see the full file list on the right.
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
Model Card for Model ID
( update august 2025 - CC-BY models are coming soon. )
Overview
This is a family of low-latency streaming models designed for use on edge devices.
Goal: Provide faster or higher-quality performance compared to similarly sized Whisper and other models.
- Languages: English, French, German (7 more languages coming).
Demos
- Browser Demo (CPU)
(Runs entirely in the browser using CPU.) - Gradio / Python Demo
License
The license is still under consideration (likely Coqui). The model is intended to be dual-licensed:
- Free for non-commercial use.
- Affordable license for commercial use.
Training
- Training is done with a modified k2/Icefall pipeline.
- Inference can be performed with the standard Sherpa project.
- Silence padding and volume normalization may help produce better results.
Acknowledgements
Special thanks to the Lhotse, Sherpa, k2, and Icefall teams for their support and tools.
Model info
Created: 2025-08-23
Updated: 2025-08-23
View on Hugging Face