Final Project code
Speech Language Recognition
Two languages (English and Chinese) with the Preprocessed Melp data
model.py -----> Classification model
data_load.py -----> Return the train_loader, val_loader, test_loader, in_channels, feature_size
main.py -----> Training and saving the model (using the best hyperparameters to training)
predict.py -----> Return the test_label
optimize.py -----> Find the best hyperparameters
transformer_long_and_short.ipynb
save_models/model_transformer_v_final.pth