alphacep / vosk-server

WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries
Apache License 2.0
896 stars 243 forks source link

how to stop detect speech by using vosk in freeswitch #100

Open chubenli opened 3 years ago

chubenli commented 3 years ago

Hi,

When I use VOSK on Freeswitch, how do I stop VOSK speech recognition when I get the results I want during a call?

I am having a problem now, I do not know how to stop VOSK speech recognition after I use VOSK to recognize the result in Freeswitch.

I've tried two approaches:

  1. Add the app to the dialplan,like this:

    <condition field="destination_number" expression="^.*$">
          <action application="answer"/>
          <action application="set" data="fire_asr_events=true"/>
          <action application="detect_speech" data="vosk default default"/>
          <action application="sleep" data="1000"/>
          <action application="detect_speech" data="stop"/>
          <action application="sleep" data="10000000"/>
        </condition>

    Or

    <condition field="destination_number" expression="^.*$">
          <action application="answer"/>
          <action application="set" data="fire_asr_events=true"/>
          <action application="detect_speech" data="vosk default default"/>
          <action application="sleep" data="1000"/>
      <action application="detect_speech" data="pause"/>
          <action application="sleep" data="10000000"/>
        </condition>
  2. use Inline Dialplan, like this:

bgapi originate {fire_asr_events=true,detect_speech=vosk}user/1001 'set:fire_asr_events=true,detect_speech:vosk default default,transfer:callcenter01 XML call_center_context,sleep:1000,detect_speech:stop' inline

But neither method can stop the recognition of VOSK, and you have to hang up the call to stop the recognition.

So, what should I do to stop Vosk speech recognition at any time?

chubenli commented 3 years ago

hi, Is anyone working on this problem?

KamleshMedankar commented 2 months ago

Hi @chubenli i want to use vosk or mod_whishper for speech to text in freeswitch i am getting difficulties pls guide me how you have perform them in freeswitch