Shypd.aiThe largest open index of AI toolskaldi-gstreamer-server is an Open Source speech recognition server that provides real-time full-duplex speech recognition. It is based on the Kaldi toolkit and GStreamer framework, implemented in Python for scalable, real-time processing.
Trending
About
kaldi-gstreamer-server is an open-source, real-time full-duplex speech recognition server built upon the Kaldi toolkit and GStreamer framework, implemented in Python. It offers highly scalable architecture with a master component and independent workers, allowing for unlimited parallel recognition sessions. Key features include support for arbitrarily long speech input, speech segmentation based on silences, and compatibility with Kaldi's GMM and online DNN models. The server also supports rescoring recognition lattices with large language models and persisting acoustic model adaptation states. It can handle various audio codecs supported by GStreamer and allows for rewriting raw recognition results using external programs. Clients are available for Python, Java, Javascript, and Haskell.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
