-
Hi, thank you for sharing this.
I have a custom dataset with monophonic events (no overlapping events). The annotation labels are stored in the same format as in this challenge:
`[filename (str…
-
When I run the code below, this process run out the cpu resource.
There are 32 processors. And the 'top' command results is shown
%CPU %MEM TIME+ COMMAND
3198 0.1 6:53.12 python extra…
-
@jmvalin Thanks for hosting this interesting project. As part of the usecases for LPCNet you mention about TTS(Text-To-Speech). How do we synthesis speech from text using the test_lpcnet.py?
If th…
-
Hi Andy,
Thanks for all the amazing works!
I just have a question about the Mockingjay model. It is mentioned in the paper that a linear-scale spectrogram is also used as the output reconstruction t…
-
Hi. marco. I cloned this project and predicted some wav files, but I ran into this problem. How should I solve this problem? thanks in advance.
```
Traceback (most recent call last):
File "/data/pr…
-
I'm testing the win_length option using version 0.1.2.dev3 and 0.1.4a0. For both versions, I got an error when instantiating MelSpectrogram with this option.
>>> mel = Spectrogram.MelSpectrogram(s…
-
Hi~
I want to check voice by combining your fastspeech, fastspeech2 and nvidia-waveglow [waveglow](https://github.com/NVIDIA/waveglow)
When training waveglow, if I train with min ~ max (80~7…
-
Windows 10.
Python 3.8.10
git `dev` of this repo
During training:
```
.\Scripts\python .\TTS\bin\train_tacotron.py --config_path config.json
```
> Using CUDA: True
> Number of GPUs…
avaer updated
3 years ago
-
Hi Maigo,
How do you get filterbank features from audios? I didn't find any code related to data processing and the data downloaded from the bash file is already prepared.
-
It is I, again. I hope it's okay to bug you here with a general question.
I want to use kapre layers to convert an audio input to mfcc directly in the model. I spent some time digging through the …
Mxgra updated
4 years ago