add natural/guided eval option

hparams.py

@@ -142,6 +142,8 @@
 
 	tacotron_zoneout_rate = 0.1, #zoneout rate for all LSTM cells in the network
 	tacotron_dropout_rate = 0.5, #dropout rate for all convolutional layers + prenet
+
+	natural_eval = True, #Whether to use 100% natural eval (to evaluate Curriculum Learning performance) or with same teacher-forcing ratio as training (just for overfit)
 
 	#Decoder RNN learning can take be done in one of two ways:
 	#	Teacher Forcing: vanilla teacher forcing (usually with ratio = 1). mode='constant'
@@ -224,4 +226,4 @@
 def hparams_debug_string():
 	values = hparams.values()
 	hp = ['  %s: %s' % (name, values[name]) for name in sorted(values) if name != 'sentences']
-	return 'Hyperparameters:\n' + '\n'.join(hp)
+	return 'Hyperparameters:\n' + '\n'.join(hp)