Incompatible Shapes Error when Training Wavenet about tacotron-2 HOT 5 CLOSED

input_type="raw",
quantize_channels=2 ** 16,  # 65536 (16-bit) (raw) or 256 (8-bit) (mulaw or mulaw-quantize) // number of classes = 256 <=> mu = 255

log_scale_min=float(np.log(1e-14)), #Mixture of logistic distributions minimal log scale
log_scale_min_gauss = float(np.log(1e-7)), #Gaussian distribution minimal allowed log scale

#To use Gaussian distribution as output distribution instead of mixture of logistics, set "out_channels = 2" instead of "out_channels = 10 * 3". (UNDER TEST)
out_channels = 2, #This should be equal to quantize channels when input type is 'mulaw-quantize' else: num_distributions * 3 (prob, mean, log_scale).
layers = 30, #Number of dilated convolutions (Default: Simplified Wavenet of Tacotron-2 paper)
stacks = 3, #Number of dilated convolution stacks (Default: Simplified Wavenet of Tacotron-2 paper)
residual_channels = 512,
gate_channels = 512, #split in 2 in gated convolutions
skip_out_channels = 256,
kernel_size = 3,

cin_channels = 80, #Set this to -1 to disable local conditioning, else it must be equal to num_mels!!
upsample_conditional_features = True, #Whether to repeat conditional features or upsample them (The latter is recommended)
upsample_scales = [15, 20], #prod(upsample_scales) should be equal to hop_size
freq_axis_kernel_size = 3,
leaky_alpha = 0.4,

gin_channels = -1, #Set this to -1 to disable global conditioning, Only used for multi speaker dataset. It defines the depth of the embeddings (Recommended: 16)
use_speaker_embedding = True, #whether to make a speaker embedding
n_speakers = 5, #number of speakers (rows of the embedding)

use_bias = True, #Whether to use bias in convolutional layers of the Wavenet

Exiting due to exception: assertion failed: [] [Condition x == y did not hold element-wise:] [x (model/inference/strided_slice_5:0) = ] [14100] [y (model/inference/strided_slice_6:0) = ] [12925]
	 [[Node: model/inference/assert_equal/Assert/Assert = Assert[T=[DT_STRING, DT_STRING, DT_STRING, DT_INT32, DT_STRING, DT_INT32], summarize=3, _device="/job:localhost/replica:0/task:0/device:CPU:0"](model/inference/assert_equal/Equal/_27, model/loss/assert_equal_2/Assert/Assert/data_0, model/loss/assert_equal_2/Assert/Assert/data_1, model/inference/assert_equal/Assert/Assert/data_2, model/inference/strided_slice_5/_29, model/inference/assert_equal/Assert/Assert/data_4, model/inference/strided_slice_1/_31)]]
	 [[Node: model/inference/residual_block_cin_conv_layer_ResidualConv1dGLU_9/assert_equal/Assert/Assert/_324 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_1801_...ert/Assert", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]]

Caused by op 'model/inference/assert_equal/Assert/Assert', defined at: