def load(self,
checkpoint_path,
num_speakers=2,
checkpoint_step=None,
inference_prenet_dropout=True,
model_name='tacotron'):
self.num_speakers = num_speakers
if os.path.isdir(checkpoint_path):
load_path = checkpoint_path
checkpoint_path = get_most_recent_checkpoint(
checkpoint_path, checkpoint_step)
else:
load_path = os.path.dirname(checkpoint_path)
print('Constructing model: %s' % model_name)
inputs = tf.placeholder(tf.int32, [None, None], 'inputs')
input_lengths = tf.placeholder(tf.int32, [None], 'input_lengths')
batch_size = tf.shape(inputs)[0]
speaker_id = tf.placeholder_with_default(
tf.zeros([batch_size], dtype=tf.int32), [None], 'speaker_id')
load_hparams(hparams, load_path)
hparams.inference_prenet_dropout = inference_prenet_dropout
with tf.variable_scope('model') as scope:
self.model = create_model(hparams)
self.model.initialize(inputs=inputs,
input_lengths=input_lengths,
num_speakers=self.num_speakers,
speaker_id=speaker_id,
is_training=False)
self.wav_output = inv_spectrogram_tensorflow(
self.model.linear_outputs, hparams)
print('Loading checkpoint: %s' % checkpoint_path)
sess_config = tf.ConfigProto(allow_soft_placement=True,
intra_op_parallelism_threads=1,
inter_op_parallelism_threads=2)
sess_config.gpu_options.allow_growth = True
self.sess = tf.Session(config=sess_config)
self.sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(self.sess, checkpoint_path)
def load(self, checkpoint_path: object, model_name: object = 'tacotron') -> object:
print('Constructing model: %s' % model_name)
self.model_filename = checkpoint_path
if not checkpoint_path.endswith('.pb'):
inputs = tf.placeholder(tf.int32, [None, None], 'inputs')
input_lengths = tf.placeholder(tf.int32, [None], 'input_lengths')
with tf.variable_scope('model') as scope:
self.model = create_model(model_name, hparams)
self.model.initialize(inputs, input_lengths)
self.wav_output = audio.inv_spectrogram_tensorflow(self.model.linear_outputs)
# self.wav_output = self.model.linear_outputs[0]
print('Loading checkpoint: %s' % checkpoint_path)
# self.session = tf.Session()
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.1)
self.session = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
self.session.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(self.session, checkpoint_path)
else:
model_filename = checkpoint_path
with open(model_filename, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
graph = tf.get_default_graph()
tf.import_graph_def(graph_def, name='')
self.inputs = graph.get_tensor_by_name("inputs:0") # 在训练的时候其实可以自己设置
self.input_lengths = graph.get_tensor_by_name("input_lengths:0")
self.wav_output = graph.get_tensor_by_name("model/griffinlim/Squeeze:0")
print('Loading pb: %s' % model_filename)
# self.session = tf.Session()
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.1)
self.session = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
self.session.run(tf.global_variables_initializer())
