Testing on WAV files from Youtube? about emotion-recognition-using-speech HOT 3 CLOSED

I haven't changed anything in the code. I have written some scripts for my own usage. The program works fine for the provided .wav files in the data sets. However, in my case, the program terminates without any prediction or probability score being printed in the console.

from emotion-recognition-using-speech.

Hi @maximtolea ,

Before using any outsider audio file, you need to first convert its sample rate to 16000Hz and mono channel, I've provided the script create_wavs.py for that case. Note that you'll need to have ffmpeg installed in your machine in order to properly convert the audio files.

Hope this helps. Let me know when this solves your issue.

from emotion-recognition-using-speech.

Hey again,

I've updated the code to automatically convert to the appropriate format when using the predict() method. Pull the repo again and check it out!

Thanks, closing the issue.

from emotion-recognition-using-speech.