train and validation accuracy -- straight horizontal lines

Question

After training the below model and plotting the train and validation accuracy I'm getting two straight horizontal lines (picture attached). These are the parameters

Params: mid_units: 256.0 activation: relu dropout: 0.34943936277356535 optimizer: adam batch_size: 64.0

for cls in os.listdir(path):
        for sound in tqdm(os.listdir(os.path.join(path, cls))):
         wav  = librosa.load(os.path.join(os.path.join(path, cls, sound)), sr=16000)[0].astype(np.float32)
         tmp_samples.append(wav)
         tmp_labels.append(cls)
         

    
    X_train, X_test, y_train , y_test  = train_test_split( tmp_samples, tmp_labels , test_size=0.60,shuffle=True) 
    
    X_test,X_valid, y_test ,   y_valid  = train_test_split( X_test, y_test , test_size=0.50,shuffle=True) 
    
   
    
    
    
    for x,y in zip(X_train,y_train):
        
         extract_features_with_aug(x, y, model, samples , labels )
         
    for x,y in zip(X_test,y_test):
       
        extract_features(x, y, model, plain_samples , plain_labels )
        
    for x,y in zip(X_valid,y_valid):
       
        extract_features(x, y, model, valid_sample,valid_label)
          
            

    X_train = np.asarray(samples)  
    y_train = np.asarray(labels)
    X_test = np.asarray(plain_samples) 
    y_test=np.asarray(plain_labels) 
    X_valid = np.asarray(valid_sample) 
    y_valid=np.asarray(valid_label) 
    
    
    X_train = shuffle(samples)  
    y_train = shuffle(labels)
    X_test = shuffle(plain_samples) 
    y_test=shuffle(plain_labels) 
    X_valid = shuffle(valid_sample) 
    y_valid=shuffle(valid_label) 
   
            
    return X_train, y_train , X_test ,  y_test ,X_valid,y_valid

Model:

input = layers.Input( batch_shape=(None,1024,1),dtype=tf.float32,name='audio') 

   
    drop=layers.Dropout( dropout_rate ) (input)
    fl= layers.Flatten() (drop)
    l= layers.Dense( mid_units , activation= activation )(fl)
    ba=layers.BatchNormalization() (l)
    drop2=layers.Dropout( dropout_rate  ) (ba)
    net=layers.Dense( 5, activation= activation )(drop2)
    model = Model(inputs=input, outputs=net)
    model.summary()
    
    return model

def train_model(
                X_train, y_train , X_test ,  y_test , X_valid,y_valid,
                fname,  # Path where to save the model
                mid_units, 
                activation , 
                dropout ,
                batch_size , 
                optimizer 

                ):

    # Generate the model
    general_model = create_model( mid_units, activation , dropout )

    general_model.compile(optimizer=  optimizer , loss='categorical_crossentropy',
                          metrics=['accuracy'])

    # Create some callbacks
    callbacks = [tf.keras.callbacks.ModelCheckpoint(filepath=fname, monitor='val_loss', save_best_only=True),
                 tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.95, patience=5, verbose=1,
                                                      min_lr=0.000001)]
    
################
    
    
    history = general_model.fit(X_train, y_train, epochs=EPOCHS, validation_data = ( X_valid,y_valid ), batch_size= batch_size ,
                                callbacks=callbacks, verbose=1)

For the training history I'm getting fixed values 3027/3027 [==============================] - 29s 9ms/step - loss: nan - accuracy: 0.2150 - val_loss: nan - val_accuracy: 0.2266 Epoch 97/100 3027/3027 [==============================] - 31s 10ms/step - loss: nan - accuracy: 0.2150 - val_loss: nan - val_accuracy: 0.2266 Epoch 98/100 3027/3027 [==============================] - 41s 14ms/step - loss: nan - accuracy: 0.2150 - val_loss: nan - val_accuracy: 0.2266 Epoch 99/100 3027/3027 [==============================] - 32s 11ms/step - loss: nan - accuracy: 0.2150 - val_loss: nan - val_accuracy: 0.2266 Epoch 100/100