CMU Sphinx / Forums / Help: Transcription and Config problem

Speech Recognition Toolkit

Transcription and Config problem

Forum: Help

Created: 2007-11-22

Updated: 2012-09-22

  I just tried to recognize 10 words and i recorded my voice and tried to train but the trainer the baum welch iteration is not going beyond 0% and moves on . i just want it to recognize my voice .

          1)Before training is there any configuration changes must be made?
          2)is there any minimum number of speech files that sphinxtrain needs to train ?
          3)i have recorded all the words in a single wav file and i have given in transcription &lt;sil&gt; for both long silence and short silence between the words. should i put &lt;sil&gt; &lt;sil&gt; for long silence ?

    i am really facing a terrible time and i need help.

    thank you guys,

Balaji.S.B.

Transcription and Config problem

Speech Recognition Toolkit

Forums

Help

Transcription and Config problem document.SUBSCRIPTION_OPTIONS = { "thing": "topic", "subscribed": false, "url": "subscribe", "icon": { "css": "fa fa-envelope-o" } };

Transcription and Config problem