kaldi-gstreamer-server
kaldi-gstreamer-server copied to clipboard
alumae
Real-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
I am exposing my local server through ngrok and ssh. I am using kaldi-gstreamer. Worker output when I speak through the mic ``` 2020-05-28 02:32:43 - INFO: __main__: Opened websocket...
When I use python 3, Python 3.6.5 there will be ERROR shown `ERROR:decoder2:(gerror=GLib.Error('Your GStreamer installation is missing a plug-in.', 'gst-core-error-quark', 12), debug='gstdecodebin2.c(4640): gst_decode_bin_expose (): /GstPipeline:pipeline0/GstDecodeBin:decodebin:\nno suitable plugins found:\nMissing decoder: WAV...
We currently deploy our own customized ASR that recognizes single-word vocabularies for our client. On the client side we have deployed our own SDK along with webrtc-vad (from chromium) to...
The different gstreamer versions available only use nnet2 decoder. Is there a way I can use nnet3 decoder with nnet3 model. I know about the nnet3 mode but it's not...
I'm using the py3 branch with the tedlium_nnet_ms_sp_online model. I'm running this on the Bill Gates TED talk mp3. Is recognizes the first few characters but then crashes: ``` Received...
On the py3 branch `decoder_test.py` still uses Python 2 print syntax.
Is it possible to alter the properties of the kaldinnet2onlinedecoder gstreamer element while it is in the pipeline? I'm trying to alter the server so I can send a request...
Hi I was able to implement the gstkaldi decoder successfullly. I have train a chain model on my own data and modified the yaml according to the sample_chinese_nnet3.yaml. However, I...
README.MD says that libgstkaldi.so should be contained in src/gst-plugin but I don't have the file, Is the information outdated? I only have: gst-audio-source.cc, .h and .o gst-online-gmm-decode-faster.cc, .h and .o...
 Thanks for any help
