solution about RuntimeError: isDifferentiableType(variable.scalar_type()) about fastspeech2

@Mao-JianGuo your solution can fix the error occured in training step

But, when the model is trained out, excuting synthesize.py would report the error below:

Traceback (most recent call last):
File "synthesize.py", line 99, in
synthesize(model, waveglow, melgan, text, sentence, prefix='step_{}'.format(args.step))
File "synthesize.py", line 47, in synthesize
mel, mel_postnet, log_duration_output, f0_output, energy_output, _, _, mel_len = model(text, src_len)
File "/home/op/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/op/.local/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 153, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/op/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/op/repo/github.com/ming024/FastSpeech2/fastspeech2.py", line 39, in forward
encoder_output, src_mask, mel_mask, d_target, p_target, e_target, max_mel_len)
File "/home/op/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/op/repo/github.com/ming024/FastSpeech2/modules.py", line 51, in forward
pitch_embedding = self.pitch_embedding(torch.bucketize(nn.Parameter(pitch_prediction), nn.Parameter(self.pitch_bins)))
RuntimeError: isDifferentiableType(variable.scalar_type()) INTERNAL ASSERT FAILED at "/pytorch/torch/csrc/autograd/functions/utils.h":59, please report a bug to PyTorch.

[Curry-AI]

In modules.py change
pitch_embedding = self.pitch_embedding(torch.bucketize(pitch_prediction, self.pitch_bins))
energy_embedding = self.energy_embedding(torch.bucketize(energy_prediction, self.energy_bins))

to
pitch_embedding = self.pitch_embedding(torch.bucketize(torch.tensor(pitch_prediction.data), self.pitch_bins))
energy_embedding = self.energy_embedding(torch.bucketize(torch.tensor(energy_prediction.data), self.energy_bins))

It worked!!! Thank you very much.

Now, I know the reason of this reported err.
The torch version author used is "torch==1.6.0.dev20200428".

[ming024]

Thank you all, closed #14