alumae/kaldi-gstreamer-server

Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.

51
/ 100
Established

Supports WebSocket-based streaming with partial hypothesis updates, automatic audio segmentation on silence, and lattice rescoring with large language models. The architecture uses a master-worker pattern enabling horizontal scaling across machines, with workers handling individual recognition sessions independently using either GMM-HMM or DNN-based acoustic models. Includes built-in post-processing hooks for result transformation and multiple client SDKs (Python, Java, JavaScript, Haskell).

1,092 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,092

Forks

339

Language

Python

License

BSD-2-Clause

Last pushed

Jun 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/alumae/kaldi-gstreamer-server"

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