1. Select Your Word List: 1 min

Demo model is designed that the you can checkout the accuracy and get an idea of the process. Open Gym software and set the word list to demo.

2. Record Audio Samples: 45 mins

For demo model we recommend recording about 400 samples. Sample means an audio .wav file consisted of three spoken words. Start recording by pressing space.

Info

When the recording starts three words will be shown up on the screen and you have 3 seconds to say them. The time will be shown up on the screen. For best performance try to say the words not close to the edges, so give a small pause after start and try to finish up 200ms before time up.

Record

2. Training The Model: 15 mins

  1. Train your model by Pressing T.

    Train

  2. Wait for Generate Enn Sample dialog to show up, this could take a while. Select No in the two following dialogs.

    Hint

    Generate Enn Samples is only required for training neural network. You can skip this for now. To learn more about these features please checkout Advanced Training.

    GenENN

  3. Congrats! Your model is now ready.

More Info

A detailed description of Gym functionalities is discussed in the Gym User Guide.