ga642381 / fastspeech2 Goto Github PK

Hello authors,
First of all, thank you for giving us an impressive repository.
For now, I want to re-trained your model with Korean language, for example KSS (korean single speaker). However, when I synthesize, I see it is not good for korean language. Can you give me some guidelines for that.

Thank you very much

VCTK. Model training OK. Run synthesize.py

Additional diagnostic just before crash:

print("Print")
print(text)
print(src_len)
print(spk_ids)

Using cache found in /root/.cache/torch/hub/descriptinc_melgan-neurips_master
Synthesizing...
Weather forecast for tonight: dark
|{W EH1 DH ER0 F AO1 R K AE2 S T F AO1 R T AH0 N AY1 T D AA1 R K}|
Print
tensor([[144, 94, 91, 97, 104, 78, 130, 116, 71, 131, 133, 104, 78, 130,
133, 73, 119, 86, 133, 90, 66, 130, 116],
[144, 94, 91, 97, 104, 78, 130, 116, 71, 131, 133, 104, 78, 130,
133, 73, 119, 86, 133, 90, 66, 130, 116],
[144, 94, 91, 97, 104, 78, 130, 116, 71, 131, 133, 104, 78, 130,
133, 73, 119, 86, 133, 90, 66, 130, 116]], device='cuda:0')
tensor([23, 23, 23], device='cuda:0')
tensor([5, 6, 7], device='cuda:0')
Traceback (most recent call last):
File "synthesize.py", line 168, in
synthesize(model, waveglow, melgan, text, sentence, prefix='step_{}'.format(args.step))
File "synthesize.py", line 85, in synthesize
mel, mel_postnet, log_duration_output, f0_output, energy_output, _, _, mel_len = model(text, src_len, speaker_ids=spk_ids)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl
return forward_call(*input, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/parallel/data_parallel.py", line 169, in forward
return self.gather(outputs, self.output_device)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/parallel/data_parallel.py", line 181, in gather
return gather(outputs, output_device, dim=self.dim)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/parallel/scatter_gather.py", line 78, in gather
res = gather_map(outputs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/parallel/scatter_gather.py", line 73, in gather_map
return type(out)(map(gather_map, zip(*outputs)))
File "/usr/local/lib/python3.8/dist-packages/torch/nn/parallel/scatter_gather.py", line 63, in gather_map
return Gather.apply(target_device, dim, *outputs)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/parallel/_functions.py", line 75, in forward
return comm.gather(inputs, ctx.dim, ctx.target_device)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/parallel/comm.py", line 235, in gather
return torch._C._gather(tensors, dim, destination)
RuntimeError: Input tensor at index 1 has invalid shape [1, 293, 80], but expected [1, 371, 80]

VCTK corpus, not all words present.

step : 1000
Epoch [1/1000], Step [1000/2688000]:
Total Loss: 2.4196, Mel Loss: 0.2047, Mel PostNet Loss: 0.2929, Duration Loss: 0.3105, F0 Loss: 72.4894, Energy Loss: 8.8656;
Time Used: 300.306s, Estimated Time Remaining: 781687.842s.
step : 2000
Epoch [1/1000], Step [2000/2688000]:
Total Loss: 1.8951, Mel Loss: 0.1795, Mel PostNet Loss: 0.1984, Duration Loss: 0.2650, F0 Loss: 48.0024, Energy Loss: 7.7215;
Time Used: 598.532s, Estimated Time Remaining: 686206.710s.
step: 2000 , length 249, tensor([249, 363, 264, 352, 281, 264, 221, 275, 264, 221, 307, 277, 298, 266,
286, 268], device='cuda:0')
Traceback (most recent call last):
File "train.py", line 265, in
main(args)
File "train.py", line 239, in main
d_l, f_l, e_l, m_l, m_p_l = evaluate(model, current_step)
File "/home/FastSpeech2/evaluate.py", line 115, in evaluate
d_l = sum(d_l) / len(d_l)
ZeroDivisionError: division by zero

Does it able to learn certain voice style?

Can you offer the Pretrained model on those LibriTTS dataset ?
Thx

File "train.py", line 109, in __init_dataset
train_loader = DataLoader(
File "/home/ssn/.local/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 344, in init
sampler = RandomSampler(dataset, generator=generator) # type: ignore[arg-type]
File "/home/ssn/.local/lib/python3.8/site-packages/torch/utils/data/sampler.py", line 107, in init
raise ValueError("num_samples should be a positive integer "
ValueError: num_samples should be a positive integer value, but got num_samples=0