Generate Depeche Mode lyrics automatically with an LSTM neural network

depeche_mode_neuralnet.py

import numpy as np
import sys
from keras.models import Sequential
from keras.layers import Dense, Dropout, LSTM
from keras.callbacks import ModelCheckpoint
from keras.utils import to_categorical

filename = 'dm_lyrics.txt'
raw_text = open(filename, 'r', encoding='utf-8').read()
raw_text = raw_text.lower()

# character-to-integer mapping
chars = sorted(list(set(raw_text)))
char_to_int = dict((c, i) for i, c in enumerate(chars))

n_chars = len(raw_text)
n_vocab = len(chars)
print('total characters: ', n_chars)
print('total vocabulary: ', n_vocab)

# prepare the dataset of input to output pairs encoded as integers
seq_length = 100
dataX = []
dataY = []

for i in range(0, n_chars - seq_length, 1):
    seq_in = raw_text[i:i+seq_length]
    seq_out = raw_text[i+seq_length]
    dataX.append([char_to_int[char] for char in seq_in])
    dataY.append(char_to_int[seq_out])
    
n_patterns = len(dataX)
print('total patterns: ', n_patterns)

''' 
    sequence input format expected by the LSTM-based neural network:
    [samples, timesteps, features]
'''
# reshape X to the expected input format
X = np.reshape(dataX, (n_patterns, seq_length, 1))

# normalization
X = X / float(n_vocab)

# one-hot encoding of the output
y = to_categorical(dataY)

print(X.shape, y.shape)

# define the LSTM model
model = Sequential()
model.add(LSTM(256, input_shape=(X.shape[1], X.shape[2]), return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(256))
model.add(Dropout(0.2))
model.add(Dense(y.shape[1], activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam')
model.summary()

filepath = 'weights_improvement_{epoch:02d}_{loss:.4f}.h5'
checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
model.fit(X, y, epochs=3, batch_size=128, callbacks=[checkpoint])