alumae / kaldi-gstreamer-server

Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
BSD 2-Clause "Simplified" License
1.07k stars 341 forks source link

Segmentation #63

Closed ersigcha23 closed 7 years ago

ersigcha23 commented 7 years ago

Hi

I want to know how can I use the segmentation feature?

Thanks

alumae commented 7 years ago

Read https://github.com/alumae/gst-kaldi-nnet2-online:

Full results can now inlude word alignment information for the best hypothesis. In order to activate this, set the word-boundary-file property to point to the word_boundary.int file typically found in the data/lang/phones/ subdirectory of a trained system.