RuntimeError: The size of tensor a (65) must match the size of tensor b (10) at non-singleton dimension 1

[niasalva]

hello
I want to train the model using python train.py --dataset VCTK command but i faced following error:

Number of Daft-Exprt Parameters: 20603604
Removing weight norm...
Training:   0%|                                                                                                                | 0/900000 [00:00<?, ?it/s
Traceback (most recent call last):                                                                                                 | 0/674 [00:00<?, ?it/s]
  File "train.py", line 190, in <module>
    main(args, configs)
  File "train.py", line 85, in main
    output = model(*(batch[2:]))
  File "/home/prosody_control/daftenv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/prosody_control/daftenv/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 161, in forward
    outputs = self.parallel_apply(replicas, inputs, kwargs)
  File "/home/prosody_control/daftenv/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 171, in parallel_apply
    return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
  File "/home/prosody_control/daftenv/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 86, in parallel_apply
    output.reraise()
  File "/home/prosody_control/daftenv/lib/python3.6/site-packages/torch/_utils.py", line 428, in reraise
    raise self.exc_type(msg)
RuntimeError: Caught RuntimeError in replica 0 on device 0.
Original Traceback (most recent call last):
  File "/home/prosody_control/daftenv/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 61, in _worker
    output = module(*input, **kwargs)
  File "/home/prosody_control/daftenv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/prosody_control/Daft-Exprt-main/model/DaftExprt.py", line 98, in forward
    p_control, e_control, d_control, src_masks, ref_mel_lens, ref_max_mel_len, ref_mel_masks, src_lens
  File "/home/prosody_control/daftenv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/prosody_control/Daft-Exprt-main/model/modules.py", line 539, in forward
    s_input = p_embed + e_embed + d_embed + encoder_outputs
RuntimeError: The size of tensor a (65) must match the size of tensor b (10) at non-singleton dimension 1

Training:   0%|                                                                                                   | 1/900000 [00:04<1071:57:08,  4.29s/it]
Epoch 1:   0%|                                                                                                                    | 0/674 [00:04<?, ?it/s]```