-
### 🚀 The feature
[TimeStretch](https://pytorch.org/audio/stable/generated/torchaudio.transforms.TimeStretch.html) is not in SpecAugment. It should be Time Warping instead. Time Warping does not chan…
-
https://github.com/zcaceres/spec_augment
This is obviously what we'd be interested in. cc' @zcaceres
-
## 🚀 Feature
Add SpecAugment as a form of audio augmentation.
## Motivation
SpecAugment (https://arxiv.org/abs/1904.08779) has resulted in huge improvements in speech recognition performance …
-
This is something I'd like someone to try (perhaps someone outside our team, as our GPUs are very busy).
It consists of modifying SpecAugment behavior, which would likely require copy-and-modify of t…
-
** Note: this issue is for the MLH fellowship **
SpecAugment is a structured dropout to be applied on MelSpectogram.
It masks some contiguous samples in the audio, as well as some continuous range…
-
I have a question about the current `SpecAugment` implementation. According to `lhotse` code, the time warping is applied only for "true" feature regions and it excludes "padded" regions i.e.
```
# …
-
When given a batch, the current SpecAugment implementation does not take the different lengths of the samples into account. It can happen that the time-mask is applied to padded areas.
The positions …
-
I got an error on from data.SpecAugment import sparse_image_warp_zcaceres could you give me some advice to solve it.
-
Hi~
I haved encountered an error when trying to enable spec-augment. The code in **librispeech.py** is：
`ep.use_specaugment = True`
The error is as below：
.
I was able to install the package, but it seems to have many code issues like typos and other small bugs.
Is there a …