🎙️A deep learning project that recognizes human emotions from speech audio using MFCC features and a CNN + LSTM architecture built with PyTorch. The project includes data preprocessing, model training, evaluation, and an interactive Streamlit application for real-time emotion prediction. Developed as part of the CodeAlpha Machine Learning Internsh
python machine-learning deep-learning cnn pytorch artificial-intelligence lstm neural-networks mfcc audio-classification librosa speech-processing audio-processing emotion-recognition speech-emotion-recognition ravdess streamlit codealpha codealpha-codealpha-machine-learning
-
Updated
Aug 4, 2026 - Jupyter Notebook