def __init__(self, model_dir):
"""Create G2P model and initialize or load parameters in session."""
self.model_dir = model_dir
# Preliminary actions before model creation.
if not (model_dir and
os.path.exists(os.path.join(self.model_dir, "model"))):
return
#Load model parameters.
num_layers, size = data_utils.load_params(self.model_dir)
batch_size = 1 # We decode one word at a time.
# Load vocabularies
self.gr_vocab = data_utils.load_vocabulary(os.path.join(self.model_dir,
"vocab.grapheme"))
self.ph_vocab = data_utils.load_vocabulary(os.path.join(self.model_dir,
"vocab.phoneme"))
self.rev_ph_vocab =\
data_utils.load_vocabulary(os.path.join(self.model_dir, "vocab.phoneme"),
reverse=True)
self.session = tf.Session()
# Create model.
print("Creating %d layers of %d units." % (num_layers, size))
self.model = seq2seq_model.Seq2SeqModel(len(self.gr_vocab),
len(self.ph_vocab), self._BUCKETS,
size, num_layers, 0, batch_size,
0, 0, forward_only=True)
self.model.saver = tf.train.Saver(tf.all_variables(), max_to_keep=1)
# Check for saved models and restore them.
print("Reading model parameters from %s" % self.model_dir)
self.model.saver.restore(self.session, os.path.join(self.model_dir,
"model"))
def load_decode_model(self):
"""Load G2P model and initialize or load parameters in session."""
if not os.path.exists(os.path.join(self.model_dir, 'checkpoint')):
raise RuntimeError("Model not found in %s" % self.model_dir)
self.batch_size = 1 # We decode one word at a time.
#Load model parameters.
num_layers, size = data_utils.load_params(self.model_dir)
# Load vocabularies
print("Loading vocabularies from %s" % self.model_dir)
self.gr_vocab = data_utils.load_vocabulary(os.path.join(self.model_dir,
"vocab.grapheme"))
self.ph_vocab = data_utils.load_vocabulary(os.path.join(self.model_dir,
"vocab.phoneme"))
self.rev_ph_vocab =\
data_utils.load_vocabulary(os.path.join(self.model_dir, "vocab.phoneme"),
reverse=True)
self.session = tf.Session()
# Restore model.
print("Creating %d layers of %d units." % (num_layers, size))
self.model = seq2seq_model.Seq2SeqModel(len(self.gr_vocab),
len(self.ph_vocab), self._BUCKETS,
size, num_layers, 0,
self.batch_size, 0, 0,
forward_only=True)
self.model.saver = tf.train.Saver(tf.global_variables(), max_to_keep=1)
# Check for saved models and restore them.
print("Reading model parameters from %s" % self.model_dir)
self.model.saver.restore(self.session, os.path.join(self.model_dir,
"model"))
def load_decode_model(self):
"""Load G2P model and initialize or load parameters in session."""
if not os.path.exists(os.path.join(self.model_dir, 'checkpoint')):
raise RuntimeError("Model not found in %s" % self.model_dir)
self.batch_size = 1 # We decode one word at a time.
#Load model parameters.
num_layers, size = data_utils.load_params(self.model_dir)
# Load vocabularies
print("Loading vocabularies from %s" % self.model_dir)
self.gr_vocab = data_utils.load_vocabulary(os.path.join(self.model_dir,
"vocab.grapheme"))
self.ph_vocab = data_utils.load_vocabulary(os.path.join(self.model_dir,
"vocab.phoneme"))
self.rev_ph_vocab =\
data_utils.load_vocabulary(os.path.join(self.model_dir, "vocab.phoneme"),
reverse=True)
self.session = tf.Session()
# Restore model.
print("Creating %d layers of %d units." % (num_layers, size))
self.model = seq2seq_model.Seq2SeqModel(len(self.gr_vocab),
len(self.ph_vocab), self._BUCKETS,
size, num_layers, 0,
self.batch_size, 0, 0,
forward_only=True)
self.model.saver = tf.train.Saver(tf.global_variables(), max_to_keep=1)
# Check for saved models and restore them.
print("Reading model parameters from %s" % self.model_dir)
self.model.saver.restore(self.session, os.path.join(self.model_dir,
"model"))
def __init__(self, model_dir):
"""Create G2P model and initialize or load parameters in session."""
self.model_dir = model_dir
# Preliminary actions before model creation.
if not (model_dir
and os.path.exists(os.path.join(self.model_dir, "model"))):
return
#Load model parameters.
num_layers, size = data_utils.load_params(self.model_dir)
batch_size = 1 # We decode one word at a time.
# Load vocabularies
self.gr_vocab = data_utils.load_vocabulary(
os.path.join(self.model_dir, "vocab.grapheme"))
self.ph_vocab = data_utils.load_vocabulary(
os.path.join(self.model_dir, "vocab.phoneme"))
self.rev_ph_vocab =\
data_utils.load_vocabulary(os.path.join(self.model_dir, "vocab.phoneme"),
reverse=True)
self.session = tf.Session()
# Create model.
print("Creating %d layers of %d units." % (num_layers, size))
self.model = seq2seq_model.Seq2SeqModel(len(self.gr_vocab),
len(self.ph_vocab),
self._BUCKETS,
size,
num_layers,
0,
batch_size,
0,
0,
forward_only=True)
self.model.saver = tf.train.Saver(tf.all_variables(), max_to_keep=1)
# Check for saved models and restore them.
print("Reading model parameters from %s" % self.model_dir)
self.model.saver.restore(self.session,
os.path.join(self.model_dir, "model"))
def __train_init(self,
params,
train_path,
valid_path=None,
test_path=None):
"""Create G2P model and initialize or load parameters in session."""
# Preliminary actions before model creation.
# Load model parameters.
num_layers, size = data_utils.save_params(params.num_layers,
params.size, self.model_dir)
# Prepare G2P data.
print("Preparing G2P data")
train_gr_ids, train_ph_ids, valid_gr_ids, valid_ph_ids, self.gr_vocab,\
self.ph_vocab, self.test_lines =\
data_utils.prepare_g2p_data(self.model_dir, train_path, valid_path,
test_path)
# Read data into buckets and compute their sizes.
print("Reading development and training data.")
self.valid_set = self.__put_into_buckets(valid_gr_ids, valid_ph_ids)
self.train_set = self.__put_into_buckets(train_gr_ids, train_ph_ids)
self.rev_ph_vocab =\
data_utils.load_vocabulary(os.path.join(self.model_dir,
"vocab.phoneme"),
reverse=True)
self.session = tf.Session()
# Create model.
print("Creating %d layers of %d units." % (num_layers, size))
self.model = seq2seq_model.Seq2SeqModel(len(self.gr_vocab),
len(self.ph_vocab),
self._BUCKETS,
size,
num_layers,
params.max_gradient_norm,
params.batch_size,
params.learning_rate,
params.lr_decay_factor,
forward_only=False)
self.model.saver = tf.train.Saver(tf.all_variables(), max_to_keep=1)
print("Created model with fresh parameters.")
self.session.run(tf.initialize_all_variables())
def __train_init(self, params, train_path, valid_path=None, test_path=None):
"""Create G2P model and initialize or load parameters in session."""
# Preliminary actions before model creation.
# Load model parameters.
num_layers, size = data_utils.save_params(params.num_layers,
params.size,
self.model_dir)
# Prepare G2P data.
print("Preparing G2P data")
train_gr_ids, train_ph_ids, valid_gr_ids, valid_ph_ids, self.gr_vocab,\
self.ph_vocab, self.test_lines =\
data_utils.prepare_g2p_data(self.model_dir, train_path, valid_path,
test_path)
# Read data into buckets and compute their sizes.
print ("Reading development and training data.")
self.valid_set = self.__put_into_buckets(valid_gr_ids, valid_ph_ids)
self.train_set = self.__put_into_buckets(train_gr_ids, train_ph_ids)
self.rev_ph_vocab =\
data_utils.load_vocabulary(os.path.join(self.model_dir,
"vocab.phoneme"),
reverse=True)
self.session = tf.Session()
# Create model.
print("Creating %d layers of %d units." % (num_layers, size))
self.model = seq2seq_model.Seq2SeqModel(len(self.gr_vocab),
len(self.ph_vocab), self._BUCKETS,
size, num_layers,
params.max_gradient_norm,
params.batch_size,
params.learning_rate,
params.lr_decay_factor,
forward_only=False)
self.model.saver = tf.train.Saver(tf.all_variables(), max_to_keep=1)
print("Created model with fresh parameters.")
self.session.run(tf.initialize_all_variables())