search

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 339 forks source link

single word audio file gives multiple results, how to choose the correct result? #240

Closed ajaysg-zz closed 4 years ago

ajaysg-zz commented 4 years ago

for example in the screenshot, Screenshot from 2020-06-03 23-06-40 when I test the audio file containing the word replace, I am getting multiple results, but at some point of time the decoder gives replace. How to print the correct result?

alumae commented 4 years ago

The lines before the last one represent intermediate results. The last line is the final result. You should study the client.py source code, it's not that difficult.