import keras.preprocessing.text.Tokenizer as Tokenizer

data = ["Two little dicky birds",
        "Sat on a wall,",
        "One called Peter,",
        "One called Paul.",
        "Fly away, Peter,",
        "Fly away, Paul!",
        "Come back, Peter,",
        "Come back, Paul."]

# Preprocess data
tokenizer = Tokenizer()
tokenizer.fit_on_texts(data)
vocab = tokenizer.word_index
seqs = tokenizer.texts_to_sequences(data)