How to Make a Speech Emotion Recognizer Using Python And Scikit-learn

To run this, you need to:

It is already trained, you can use test.py to test your voice.

You can:

Tweak the model parameters ( or the whole model ) in ser.py.
Add more data to data folder in condition that the audio samples are converted to 16000Hz sample rate and mono channel, convert_wavs.py does that.
Editing the emotions specified in utils.py in AVAILABLE_EMOTIONS constant.

When you modified anything, you can run ser.py to retrain the model.

If you want to only use this efficiently, definitely check Emotion Recognition using Speech repository which ease this process a lot.

Name		Name	Last commit message	Last commit date
Latest commit History 11 Commits
.idea		.idea
__pycache__		__pycache__
confusion_matrix		confusion_matrix
emo_db		emo_db
plots		plots
result		result
.gitignore		.gitignore
README.md		README.md
avalicao.py		avalicao.py
basic_neuralNetwork.py		basic_neuralNetwork.py
best_model.h5		best_model.h5
best_model_cnn1d.h5		best_model_cnn1d.h5
best_model_cnn2d.h5		best_model_cnn2d.h5
cnn1d_lflb.py		cnn1d_lflb.py
cnn2d_lflb.py		cnn2d_lflb.py
cnn2d_lflb_crossval.py		cnn2d_lflb_crossval.py
convert_wavs.py		convert_wavs.py
datasets.py		datasets.py
models.py		models.py
random_forest.py		random_forest.py
requirements.txt		requirements.txt
results.txt		results.txt
svm.py		svm.py
test.py		test.py
testando_audios.py		testando_audios.py
testando_lda.py		testando_lda.py

Provide feedback