vosk-server
vosk-server copied to clipboard
alphacep
WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries
I was looking for a way to update the recognizer vocabulary in runtime on the vosk-server and I found "test_words.py", so I was hoping that it does the job. Unfortunately...
Hi, I'm trying to capture and to record a voice in the browser. Looks like modern browsers (at least Firefox and Chrome) don't support recording `audio/wav`. Is it possible to...
Hello -- when trying to send live audio to vosk-server kaldi-en running on a remote server using the following code on the rPi client... `arecord --buffer-time=5000000 -D plughw:2,0 -f cd...
Hi ! I'm coming from https://alphacephei.com/nsh/2020/10/21/french.html I'm using the _linto-platform-stt-standalone-worker-streaming_ project, with the v2 models of LinTO (_linSTT_AM_fr-FR_v2.0.0 + decoding_graph_fr-FR_Medium_v2.1.0_) I got pretty good results, but I see your post...
Hi, The input stream is likely to be overflowed and not closed. Assign a close stream to it
I am testing the Webrtc server version on the AWS server. but I am getting this error on the server-side(python) and the browser is not getting any stt result. I...
Hi, I've tried to use angular demo it seems a bit old and does not work properly. Here is what I'm getting when I try to use it. 
For now we support Chrome only and require TTS for the demo. It would be nice to provide visual feedback instead and support other browsers like Mozilla and Chromium (IE...
I spent some time to understand why I got ``` kaldi_1 | Error in connection handler kaldi_1 | Traceback (most recent call last): kaldi_1 | File "/usr/lib/python3/dist-packages/websockets/server.py", line 169, in...
