XiaoMi/kaldi-onnx

Kaldi model converter to ONNX

48
/ 100
Emerging

This tool helps speech recognition engineers convert their Kaldi neural network models into a format suitable for deployment on various devices. You provide your trained Kaldi Nnet2 or Nnet3 text models, and it outputs ONNX models. This is ideal for teams who have developed speech recognition systems using Kaldi and now need to efficiently deploy them on mobile, desktop, or embedded hardware.

247 stars. No commits in the last 6 months.

Use this if you need to take your existing Kaldi-trained speech recognition models and optimize them for faster, more portable inference on a variety of devices, especially mobile.

Not ideal if you are looking for a tool to train new speech recognition models or if you don't use Kaldi as your primary speech recognition toolkit.

speech-recognition model-deployment mobile-AI edge-AI acoustic-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

247

Forks

60

Language

Python

License

Apache-2.0

Last pushed

Jan 27, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/XiaoMi/kaldi-onnx"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.