error in new commit about fastspeech HOT 9 OPEN

if i run it on Gpu it gives same traceback with this error.
in torch 1.2.0 :
RuntimeError: invalid argument 6: wrong matrix size at /pytorch/aten/src/THC/generic/THCTensorMathBlas.cu:499

in torch 1.5.0 last line of same error is
RuntimeError: invalid argument 6: wrong matrix size at /pytorch/aten/src/THC/generic/THCTensorMathBlas.cu:549

from fastspeech.

Hi, an error occured to me when running preprocess.py with the latest code version. It seems the processing is jammed as shown in the following picture. Have you had this error? if yes, could you introduce your solutions?

from fastspeech.

Hi, an error occured to me when running preprocess.py with the latest code version. It seems the processing is jammed as shown in the following picture. Have you had this error? if yes, could you introduce your solutions?

futures.append(_process_utterance(out_dir, index, wav_path, text)) index = index + 1 return futures

from fastspeech.

But what's the reason for this "deadlock" in the current code(with executor.submit....)?

from fastspeech.

It seems because there are torch tensor operations in multi processing. I located that the code came to a deadlock when running the line as shown in the following picture. If I replace torch.FloatTensor with array, it passes. Could someone explain it?

from fastspeech.

It seems because there are torch tensor operations in multi processing. I located that the code came to a deadlock when running the line as shown in the following picture. If I replace torch.FloatTensor with array, it passes. Could someone explain it?

Because of the version of pytorch?

from fastspeech.

hi @xcmyz, it seems this issue opened by @Ahmad-noborders is also reproduced here in my case. By printing the Tensors out, I find unresolved mismatches between the sizes of "duration" Tensors from the dataset and the "out" Tensors produced by DurationPredictor().

from fastspeech.

@Ahmad-noborders were you able to resolve the issue?

from fastspeech.

@singhaki nope i had to move to tacotron2 which is base of this repo

from fastspeech.