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.
The envrionment is Centos 7,I have read your readme and download all neccessary packpages,but I still can not run it successfully.  It seems that I need download concurrent or...
I had setup the worker and server and it works fine but when i send audio via the HTTP api, ` curl -T test/data/english_test.wav "http://localhost:8888/client/dynamic/recognize"` the workers gives error. Here...
How can I hit the API in this curl command ``` curl -v -T /tmp/drawrectangle.mp3 "http://localhost:8080/client/dynamic/recognize"``` with ajax. can i sent the blob file for this. I just need record...
As part of my Botium Speech Processing project, I prepared a docker image for this server which actually work with newest Kaldi versions and models (https://hub.docker.com/repository/docker/botium/kaldi-gstreamer-server): https://github.com/codeforequity-at/botium-speech-processing/tree/master/opt/docker-kaldi-gstreamer-server Would be nice...
Hello, Is kaldi gstreamer support kaldi e2e model (which doesn't use i-vectors for training and thus no ivector extractor is trained). Additionally for acoustic model, kaldi gstreamer raises error for...
I trained an Urdu ASR system and after putting in the command **python kaldi-gstreamer-server/kaldigstserver/client.py -r 16000 output.wav** I am getting the following output on client terminal. ``` Audio sent, now...
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...
I noticed that the max number of processes/threads is set to 1. Not sure if it changes anything, it seems like the master is not relaying anything to multiple workers...
Hi alumae I tried your gstreamer docker and i have launched 8 workers and one master using supervisord and it is working fine. But if i do send buffers for...
Hello, Using the chain models and a yaml config file similar to sample_english_nnet2.yaml (the only major difference is "nnet-mode:3"), the transcriber is working with poor accuracy and big latency. NNET2...
