SpecAugment
SpecAugment copied to clipboard
DemisEom
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
from SpecAugment.sparse_image_warp_zcaceres import sparse_image_warp ModuleNotFoundError: No module named 'SpecAugment
When more than 1000 audio files are being fed to this tensorflow SpecAugment code using a python loop, the execution times gradually become very slow. Is there any way to...
Hi, First of all love the Library. I am having problems with importing spec_augment_pytorch. The issue is with importing matplotlib same as this post: [link](https://stackoverflow.com/questions/55811545/importerror-cannot-load-backend-tkagg-which-requires-the-tk-interactive-fra) But as its in the...
Hi, Do you have any suggestion about how to re-build the audio file after augmentation?
Hello, I'm wondering how the log-mel spctrograms are normalized to have zero mean value. The paper mentioned about it, and the masking value is 0 because they have zero mean....
Any idea on how to resolve this problem? ``` from SpecAugment import spec_augment_pytorch as spec_augment_l import librosa y, sr = librosa.load(dataset_audio_path.joinpath(audio_path), sr=16000) y, _ = librosa.effects.trim(y, top_db=15) S = librosa.feature.melspectrogram(y,...
the same audio, when I use librosa.feature.melspectrogram to extracte log mfcc, says Matrix A(43,N). But it turns out that Matrix A is not equal as kaldi's mfcc extraction, says Matrix...
Hi, I was trying to use SpecAugment (just run a simple augmentation for now). I was able to install the package, but it seems to have many code issues like...
