-
Using model: Tacotron
Using device: cuda
Initialising Tacotron Model...
\Loading the json with %s
{'sample_rate': 16000, 'n_fft': 800, 'num_mels': 80, 'hop_size': 200, 'win_size': 800, 'fmin'…
-
Traceback (most recent call last):
File "E:\PyProjects\git_projects\MockingBird\toolbox\__init__.py", line 122, in
func = lambda: self.synthesize() or self.vocode()
File "E:\PyProjects\git…
-
I'm trying to debug echoing and overly long output audio, and in the spirit of #31 and #133, seeing if I can fix things by playing around with the start and stop symbols. The Tensorflow seq2seq docume…
-
Great to see this implementation. We're trying to leverage GPU to do the wave.net inference, while our model's R=256, and we want to see if it is easy to support it and archive real time for at least …
-
使用my_run8_25k.pt模型生成音频，但合成后的音频听起来就像是电子音
看到运行时有报错说：UserWarning: nn.functional.tanh is deprecated. Use torch.tanh instead.
不知道会不会和这个有关系
已尝试把代码中所有提到nn.functional.tanh替换为torcht.tanh代替，仍有以上报错
下附完整运行日…
-
```
python synthesize.py
RuntimeError: Failed to load checkpoint at logs-Tacotron-2/taco_pretrained/
```
Can't find where to download pretrained model in readme, i.e. I can't find model in this …
-
I am trying to get pre-trained models for other data sets. Can somebody tell me the exact steps to do pre-training?
-
I am trying long sentences (~240 English symbols) and I found that the model has troubles to start at > 80 symbols, there are two main problems:
1. flowtron (python inference.py) keeps only a small p…
-
Hi @jaywalnut310 ,
Many thanks for your work!
As usual this is very thorough, open and inspiring.
In your paper you publish the GPU speed benchmarks:
> We measured the synchronized elapsed t…
-
I used LJSpeech-1.1 data to test
1.After I have run 'Python3 wavenet_preprocess.py', I can get these files.
![default](https://user-images.githubusercontent.com/22276263/43935953-e3ee01f4-9c88-11e8-…