RuntimeError: stack expects each tensor to be equal size, but got [40, 240] at entry 0 and [78, 202] at entry 1

[khainh3101]

Hi, after preprocessing data and create alignments files by Tacotron2, I start training and get this error, can you resolve for me please ? In this case, i want to try to train an others language dataset. Thank you.
This's console error log:

Use FastSpeech
Model Has Been Defined
Number of TTS Parameters: 25367169
Load data to buffer
100%|██████████████████████████████████████████| 14139/14139 [00:06<00:00, 2245.24it/s]
cost 6.30s to load all data into buffer.
Defined Optimizer and Loss Function.
<class 'torch.Tensor'>
Traceback (most recent call last):
File "train.py", line 197, in
main(args)
File "train.py", line 83, in main
for i, batchs in enumerate(training_loader):
File "/mnt/9365f469-af3c-437f-9a58-546628b1869a/FastSpeech/fs-env/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 517, in next
data = self._next_data()
File "/mnt/9365f469-af3c-437f-9a58-546628b1869a/FastSpeech/fs-env/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 557, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/mnt/9365f469-af3c-437f-9a58-546628b1869a/FastSpeech/fs-env/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch
return self.collate_fn(data)
File "/mnt/9365f469-af3c-437f-9a58-546628b1869a/FastSpeech/FastSpeech/dataset.py", line 118, in collate_fn_tensor
output.append(reprocess_tensor(batch, cut_list[i]))
File "/mnt/9365f469-af3c-437f-9a58-546628b1869a/FastSpeech/FastSpeech/dataset.py", line 93, in reprocess_tensor
durations = pad_1D_tensor(durations)
File "/mnt/9365f469-af3c-437f-9a58-546628b1869a/FastSpeech/FastSpeech/utils.py", line 75, in pad_1D_tensor
padded = torch.stack([pad_data(x, max_len, PAD) for x in inputs])
RuntimeError: stack expects each tensor to be equal size, but got [40, 240] at entry 0 and [78, 202] at entry 1