Transformer-TTS

Transformer-TTS copied to clipboard

Bumps [numpy](https://github.com/numpy/numpy) from 1.13.3 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

Question about prepare alignments

1

Hi, In` prepare_fastspeech.ipynb` file, about ```python F = torch.mean(torch.max(alignments, dim=-1)[0], dim=-1) r, c = torch.argmax(F).item()//4, torch.argmax(F).item()%4 location = torch.max(alignments[r,c], dim=1)[1] ``` My understanding is: In the first line, the tensor...

chynphh

I ran python3 prepare_data.py with my own data (22050, 16bit, mono), AssertionError occured. HBox(children=(FloatProgress(value=0.0, max=28825.0), HTML(value=''))) Traceback (most recent call last): File "prepare_data.py", line 103, in text, char_seq, phone_seq, melspec,...

Truong-Thanh-Quang

models/loss.py", line 32, in guide_loss B, n_layers, n_heads, T, L= alignments.size()

2

what is wrong ? Thank you

Hongpeng1992

Hello, thanks for your contributions. This source code is very helpful to me and my colleagues. I got 2 questions while using this source code. 1. How much you spent...

Jackson-Kang

Better explanation of "I failed to train the fastspeech"

1

Could you elaborate a little more and maybe propose a solution to the problem you raised? (2020/02/10) I was able to finish this implementation by completing the Stop token prediction...

mellogrand

train.py fails with error "too many indices for tensor of dimension 2"

2

Training fails with following error message: ``` File "/path/to/project/Transformer-TTS/loss.py", line 33, in guide_loss W[i, :T, :L] += alignments[0].new_tensor(1-torch.exp(-12.5*x)) IndexError: too many indices for tensor of dimension 2 ```

domcross

Bumps [scipy](https://github.com/scipy/scipy) from 1.0.0 to 1.10.0. Release notes Sourced from scipy's releases. SciPy 1.10.0 Release Notes SciPy 1.10.0 is the culmination of 6 months of hard work. It contains many...

dependabot[bot]

english is well, but whether chinese is work?

1

Hello, I have used LJspeech to train model , get a good result. But when I use biaobei dataset(a public chinese dataset) to train model , get a bad result(the...

wsywsywsywsywsy979