How to know the audio parameter values that correspond to my wav files

TTS (Text-to-Speech)
#1

Hello,
I search for a way to extract my AUDIO PARAMETERS to set it in the config file, but didn’t know how.
Any one have an idea about extract audio parameters from your own dataset wav file like

// AUDIO PARAMETERS
"audio":{
    "fft_size": 1024,         // number of stft frequency levels. Size of the linear spectogram frame.
    "win_length": 1024,      // stft window length in ms.
    "hop_length": 256,       // stft window hop-lengh in ms.
    "frame_length_ms": null, // stft window length in ms.If null, 'win_length' is used.
    "frame_shift_ms": null,  // stft window hop-lengh in ms. If null, 'hop_length' is used.
  ........

Thank you.

#2

Hi, there is a notebook that you can run and it is called CheckSpectrograms. Generally the default values you will find in the original config are good ones, unless your dataset is very noisy.

2 Likes