Speech-Emotion-Analyzer

Speech-Emotion-Analyzer copied to clipboard

Inference code?

2

Hi, Thanks for the nice work. I was trying to just use your model for inference. I looked at the notebook and copied the necessary parts for inference, but get...

arianaa30

When I tried Loading the model with final_result_gender_test, I got AttributeError:'list' object has no attribute'items'. Please tell me how to resolve. OS: MacOS Big Sur Environment: VSCode Docker Ubuntu 18.0.4...

Co-Graph-Okuda

harsha0609

Using TensorFlow backend. D:/Projects/Audio/Emotion/Speech-Emotion-Analyzer/final_results_gender_test.py:97: WavFileWarning: Chunk (non-data) not understood, skipping it. sr,x = scipy.io.wavfile.read('RawData/EP03_seq04_sc133.wav') Traceback (most recent call last): File "D:/Projects/Audio/Emotion/Speech-Emotion-Analyzer/final_results_gender_test.py", line 97, in sr,x = scipy.io.wavfile.read('RawData/EP03_seq04_sc133.wav') File "D:\InstallPath\Develop\Anaconda3\5.3.1\envs\SpeechEmotionAnalyzer3.5\lib\site-packages\scipy\io\wavfile.py", line...

WestbrookZero

Recommendations for Replicability

3

The notebook `final_results_gender_test.ipynb` can benefit from some slight modifications that will allow others to replicate exactly the results: * After the label encoder is fitted, print what it looks like...

dehdari

getting the error in Getting the features of audio files using librosa it is becausee of training data is wrong?

amith-dsilva

first, thanks for your great work. that let me quickly learn much domain knowledge about how to process voice data.but i am still troubled by the model result, i use...

luanwd

Number of MFCC features is **214** for Surprised, Neutral and Disgust, but **216** for Happy, Sad, Angry , even for the **same duration** of audio file, Can you please explain

gulatisimran

dataset

5

can you send me your dataset (RawData/)? [email protected]

kailaisun

ValueError: Shapes (None, 11) and (None, 10) are incompatible

1

during the line: cnnhistory=model.fit(x_traincnn, y_train, batch_size=16, epochs=700, validation_data=(x_testcnn, y_test)) the following error occurs: ValueError: Shapes (None, 11) and (None, 10) are incompatible how do I fix this?

vibe-av