RayyanAhmed9477/speech-emotion-analyzer

Speech Emotion Analyzer Model

This is a Keras model trained for speech emotion recognition.

Model Details

The model is a Convolutional Neural Network (CNN) trained on audio features (Mel Spectrograms) to classify speech into the following emotion categories:

angry, disgust, fear, happy, neutral, sad, surprise

Usage

To use this model, you can load it using TensorFlow/Keras:

import tensorflow as tf
from huggingface_hub import hf_hub_download

repo_id = "RayyanAhmed9477/speech-emotion-analyzer"
filename = "cnn_emotion_model.keras" 

# Download the model file
model_path = hf_hub_download(repo_id=repo_id, filename=filename)

# Load the model
model = tf.keras.models.load_model(model_path)

# Now you can use the model for prediction
# (You'll need to implement feature extraction similar to the original app)

Features

• Data loading and preprocessing using the RAVDESS dataset
• Feature extraction using librosa (MFCCs and spectrograms)
• Neural network models (CNN) implemented with TensorFlow/Keras
• Model training with early stopping and comprehensive evaluation metrics
• Hyperparameter optimization