Bagus Tris Atmaja

I have opensmile-python worked in Ubuntu 16.04 (with gcc 5.4), Ubuntu 18.04 (with gcc 7.5), and Ubuntu 20.04 (gcc 9.3.0)

Use zero paddings. That's the common step in speech processing. Using keras, it only needs one line to make all utterances have the same row size. Reference: https://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/sequence/pad_sequences

See this code for accessing emotion label. https://github.com/Strong-AI-Lab/emotion/blob/21c02f1e8ce96796cf3e9281e8aa0461fe3c7479/datasets/CMU-MOSEI/process.py#L41-L70

I will make a pull request if this issue is considered. Or the author can add it, just add two lines to __init__.py ``` __version__ = '0.3.5' VERSION = __version__...

Any progress on this PR? Having SpecAugment as Keras layer would be very useful for the DL-based audio processing community...

Is the following layer is the replacement? `composed_melgram_layer = kapre.composed.get_melspectrogram_layer(input_shape=(44100, 1))` I am also looking for a compatible replacement for the Melspectrogram layer. Any information is appreciated.

I am installing this plugin for this purpose. Instead of toggling F4 key, it would be very beneficial to have nautilus follow what I did in this `nautilus terminal`. So,...

Same error here. Pdf appears but error message also appears. Already set 'pdflatex' manually in jupyter_notebook_config. This is may be the problem, no line for `c.LatexConfig.latex_command=`. I added it manually...

Facing this problem on Centos 7.9, both gcc 4.8.5 and 7.8.1. Is there any workaround?

hi @iplasma, what configuration you used to compile with elrepo kernel? I tried, but it always fails with unavailability of kernel headers (which is not possible to install with elrepo,...