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

is there any java client api for real time speech dictation #19

Closed badboys4life007 closed 9 years ago

badboys4life007 commented 9 years ago

Helllo i found there in readme file that Python, Java, Javascript clients are available on kaldi-gstreamer-server. i did not find java client sample code anywhere... is there available for real time dictation demo?

alumae commented 9 years ago

Yes, there is a Java library that contains the client API: https://github.com/Kaljurand/net-speech-api/tree/master/src/main/java/ee/ioc/phon/netspeechapi/duplex

There is an Android app Kõnele that contains a client implementation, check https://github.com/Kaljurand/K6nele/blob/master/app/src/ee/ioc/phon/android/speak/WebSocketRecognizer.java

Kaljurand commented 8 years ago

The client in Kõnele has moved to https://github.com/Kaljurand/K6nele/tree/master/app/src/ee/ioc/phon/android/speak/service

Umar17 commented 5 years ago

Dear All, I have successfully used this code for audio files. Now, I want to modify api for live mic streaming. Objective is to capture mic and decoding it online. Is there any api for that? I have captured mic and converting it into bytes array. This byte array is being passed to modified sendFile function (modify to get byte array chunk as argument). But Gstreamer, in this case, raises "Could not determine type of stream." or "Your Gstreamer installation missing plugin" error. Please guide

Best Regards

maitrungduc1410 commented 4 years ago

@Umar17 , Here I have complete and working code for decoding from microphone, python 2 and 3 are supported