-
In your demo, Melspectrogram is called with input_shape=(channel, dim),
While, In my project, 'Input' of keras is used, the default return format is (?, num_channel, num_dim), which denotes baches o…
-
**Is your feature request related to a problem? Please describe.**
librosa.filters.mel allows parameters htk and norm. I would like librosa.feature.melspectrogram to accept those parameters too.
…
-
Hello,
As of right now, if you train your TTS with certain sample rate, you can't use it with a pertained vocoder trained on an other sampling rate. (It's true with other audio parameters like hop_…
-
I have run it on Ubuntu and Windows, however, it appears this error.
Can someone he…
-
model = Sequential()
model.add(Melspectrogram(sr=SR, n_mels=128,
n_dft=512, n_hop=128, input_shape=input_shape,
return_decibel_melgram=True,
trainable_kernel=False,…
-
在windows环境下测试没有问题，但是Linux平台同样代码就会假死。 初步是认为删除librosa.mfcc或者替换librosa.load就可以正常运行，原因不明
-
hey, thanks for great paper and repo! I have only one issue with running pythonic implementation:
1) I've loaded random youtube video with talking person in .mp4 format
2) with ffmped I got both .wa…
-
For the records, while trying to debug some issues I had with a new environment I realised that my kapre melspectrogram were wrong when using **keras 2.3.1** (latest) and 2.3.0
Reverting to **keras…
-
Hello, thanks to your work, I was able to make the desired voice.
However, there is a problem that the "avg_align_error" figure does not fall below a certain number.
Adding data did not lower "avg_…
-
tensorflow 1.15.2
kapre 0.1.7
librosa 0.7.2
torchaudio 0.4.0
pytorch 1.4
Here is the script:
```
import tensorflow as tf
import tensorflow.keras as keras
import kapre
import torch
import …