Accent-Recognition-System

This git repository is an implementation of three different models for accent recognition and evaluation for the language of English

The three different models:

1. CNN and LSTM concatenated ML model:

This model is implemented in streamlit, and includes code for preprocessing the data, defining and training the CNN and LSTM layers, and evaluating the model's performance. The repository includes necessary data or resources for training and testing the model, as well as any relevant documentation or comments.

2. YamNet architecture transfer learning model:

This model is implemented in streamlit, and includes code for preprocessing the data, using the YamNet architecture as a starting point, and fine-tuning the model for the specific task at hand. The repository includes any necessary data or resources for training and testing the model, as well as any relevant documentation or comments.

3. MFCC Model to calculate distances:

This model is implemented in streamlit, and includes code for extracting MFCC features from audio data, calculating distances between pairs of MFCC features, and evaluating the performance of the model. The repository includes any necessary data or resources for training and testing the model, as well as any relevant documentation or comments.