-
I've trained a model based on the LJSpeech dataset and found the results quite satisfactory after 25000 steps in ForwardTacotron. Now, I'm currently preparing several other datasets where new models w…
-
Hi, I want to know how to set teacher forcing in GRID and TCDTIMIT dataset. The same as lip2wav dataset? teacher forcing decay from 29000 steps?
-
@keithito I've run your original code on Blizzard2012! Nothing is changed! It seem that some thing is wrong with the silence at the end.
You may take a look at the waves at different global steps fo…
-
就是接着这个大佬的模型继续训练，因为我自己的模型太过于小了，无法收敛。但是一更换就报错
截图在下面 然后我再复制粘贴一下防止我没传上来图片
E:\数据集制作\MockingBird-main\synthesizer\synthesizer_dataset.py:84: UserWarning: Creating a tensor from a list of numpy.ndarray…
-
Thanks for the great work. I have trained wavernn on Databaker mandarin dataset(about 12 hours) for about 500K steps in MOL mode. But the synthesized audio has a lot of pitter patter noise. The only c…
-
Currently fairly early into training. Only 14k steps in, already impressively the step evaluation wavs can be understood.
However when the same text is provided to synthesis.py (via hparams) it com…
-
Although both Waveglow and Taoctron2 use the same version of pytorch, on **inference** -- NOT training --, tacotron2 displays really low utilization, while Waveglow shows 100% utlization. I would ilke…
-
`python run.py --config_file=example_configs/text2speech/tacotron_gst.py --mode=infer --infer_output_file=unused`
```
*** Building graph on GPU:0
Traceback (most recent call last):
File "run.p…
-
**Summary[问题简述（一句话）]**
using version v0.0.1,and pretrained model https://pan.baidu.com/s/1PI-hM3sn5wbeChRryX-RCQ 提取码：2021,but occur issue:
ValueError: loaded state dict contains a parameter group t…
-
It seems that the generated audios cannot be longer of 12 seconds. You can try for example the text "VilaWeb fou el primer mitjà digital català en incorporar una plataforma de blogs personals fàcilmen…