OyeBI-01/Yoruba-speech-recognition

# Yoruba Speech Recognition Model # Description The yoruba speech recognition model is designed to accurately transcribe yoruba language audio to text. The model was implemented using Long Short-Term Memory (LSTM) networks on dataset gotten from OpenSLR Yoruba Speech Dataset # Tech Stack • Programming Language: Python • Machine Learning Framework: TensorFlow/Keras • Model Architecture: Long Short-Term Memory (LSTM) network for sequential audio data processing • Data Handling: Numpy, Pandas for data manipulation and preprocessing • Audio Processing: Librosa for audio loading, transformation, and feature extraction • ML Utilities: scikit-learn for preprocessing, feature extraction, and evaluation metrics • Visualization: Matplotlib (plt) for visualizing data distributions, model performance, and other insights # Application Ideal for educational tools, translation projects, cultural preservation, and natural language processing & speech recognition research involving Yoruba Language.