title: Automatic Speech Recognition using Segments
type: community
group: Audio/Speech Processing
image: /static/templates/automatic-speech-recognition-using-segments.png
details: |
  <h1>Segment voice activity and transcribe the audio</h1>
  <dl>
    <dt>Industry Applications</dt>
    <dd>call center transcription, meeting minutes, podcast transcription, lecture recordings, courtroom proceedings, medical dictation, voice assistants, subtitling, accessibility services, broadcast transcription, phone banking, voice search</dd>
    <dt>Associated Models</dt>
    <dd>Whisper, Wav2Vec2, DeepSpeech, voice activity detection, WebRTC VAD</dd>
    <dt>Domain Terminology</dt>
    <dd>VAD, speech segmentation, speech-to-text, ASR with VAD</dd>
  </dl>
config: |
  <View>
    <Labels name="labels" toName="audio">
      <Label value="Speech" />
      <Label value="Noise" />
    </Labels>

    <Audio name="audio" value="$audio"/>

    <TextArea name="transcription" toName="audio"
              rows="2" editable="true"
              perRegion="true" required="true" />
  </View>