Testing on WAV files from Youtube?

[maximtolea]

Hello,

I wanted to use this repository for calling predictions and prediction probabilities on .wav files I'm getting from the internet. I've been using converted youtube audio clips (in the final form of .wav). For some reason, basic predictions aren't being done on these files. I wanted to know if you could explain how one should properly test these new WAV files. For the time being, I've just been following example 2 in the README, downloading the files, and putting them in their own folder within the emotion-recognition-using-speech one. Is there anything in the code I should modify to be able to use this program on wav files converted from Youtube?

[maximtolea]

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.

[x4nth055]

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.

[x4nth055]

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.