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 342 forks source link

Running the client demo returns too short text #206

Open RaniRaven opened 4 years ago

RaniRaven commented 4 years ago

It seems like the client.py program is closing the websocket before all the result was sent. No idea where is the problem in the code, or why this is not happening to all the ones who are trying to use it. I cannot figure out why does it take so much time to produce the results, and if this implementation is using the GPU (it is supposed too, as I compiled Kaldi with GPU)

jiahenghuang commented 4 years ago

It seems like the client.py program is closing the websocket before all the result was sent. No idea where is the problem in the code, or why this is not happening to all the ones who are trying to use it. I cannot figure out why does it take so much time to produce the results, and if this implementation is using the GPU (it is supposed too, as I compiled Kaldi with GPU)

hello,do you solve this problem?

consde commented 4 years ago

Having the same issue. I guess the problem is on the client.py code. But I don't know how to fix this.