search

MiteshPuthran / Speech-Emotion-Analyzer

The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)
MIT License
1.29k stars 436 forks source link

Reagarding the labelling #25

Closed aningo123 closed 5 years ago

aningo123 commented 5 years ago

Can you help me in the code how you have set the labels. I am unable to detect the female emotion.

MiteshPuthran commented 5 years ago

Hello @aningo123 the labels are set based on the audio file names. The dataset website has provided the details on the creating the labels for individual audio files.

(For example, if the audio file name ends with 04 then those files belong to female actor who is portraying a sad emotion.)