mathquis/node-kaldi-online-nnet3-decoder

ASR online decoding using Kaldi NNet3 GrammarFST

27
/ 100
Experimental

This tool helps developers integrate real-time speech-to-text functionality into their applications using Kaldi's advanced neural network models and grammar-based decoding. It takes live audio streams and a predefined grammar (FST) and outputs transcribed text. Developers working on voice-enabled applications or interactive voice response (IVR) systems would find this useful.

No commits in the last 6 months.

Use this if you are a developer looking to add online, grammar-constrained automatic speech recognition (ASR) capabilities to your Node.js application, leveraging Kaldi's NNet3 models.

Not ideal if you need a pre-packaged speech-to-text service that doesn't require compilation or a deep understanding of Kaldi's architecture.

ASR development voice applications real-time transcription Node.js integration Kaldi ASR
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

8

Forks

4

Language

C++

License

Last pushed

Jul 11, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/mathquis/node-kaldi-online-nnet3-decoder"

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