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

custom language model #101

Open satell opened 6 years ago

satell commented 6 years ago

hi please I'm new to kaldi , I build and install alumae/gst-kaldi-nnet2-online and alumae/kaldi-gstreamer-server and asr is working fine using arecord -f S16_LE -r 16000 | python kaldigstserver/client.py -r 32000 - but I need to add custom language model(my command control text corpus) to it to improve the recognition accuracy for my domain , would you please help me to find a instruction guide to do this ?

best regards Ehsan

dpny518 commented 6 years ago

https://chrisearch.wordpress.com/2017/03/11/speech-recognition-using-kaldi-extending-and-using-the-aspire-model/