IndiSpeak is a machine learning project aimed at classifying audio embeddings into various Indian languages. The project leverages the power of deep learning and ensemble methods to achieve accurate language classification.
- Utilizes VGGish model for extracting audio embeddings from audio files.
- Implements Random Forest (RF) as the classification algorithm.
- Employs GridSearchCV for hyperparameter tuning to optimize model performance.
You can find the final presentation slides here.