Andreas Triantafyllopoulos

pip installable package

1

Hi @SarthakYadav thanks for the great code! I think it would be easier to use it if you would turn it into a pip-installable library. I could create a PR...

Adding Jupyter Notebook Tutorials

1

I have some nice jupyter notebook tutorials lying around. I already know how to add them to sphinx. Does anyone know how (and where) to automatically deploy them?

Invertible transforms

4

### Feature I would like to introduce invertible transforms. This means that every transform that can be inverted will have an extra function, e.g. named `inverse` that would undo the...

CMU-MOSI: Manual gesture annotations

2

In [Multimodal sentiment intensity analysis in videos: Facial gestures and verbal messages](https://ww.sentic.net/multimodal-sentiment-intensity-analysis-in-videos.pdf), there's reference to manual gesture annotations: `smile`, `frown`, `head shake`, `head nod`. Are these available through the SDK,...

Wrong video files

1

I used [this link](http://web.eecs.umich.edu/~mihalcea/downloads/MELD.Raw.tar.gz) to download the audio files for this data set. However, there are a few problems with at least a few of the video files and/or their...

Random cropping for variable length sequences

4

### 🚀 The feature I am proposing to add a `torch.nn.Module` transform that automatically crops/pads signals (with different options for padding such as constant/mirroring). I have the implementation already local...

Discrepancy in IS12_speaker_trait.conf

2

So I used the process described in #109 to extract `IS12_speaker_trait` functional features using the wrapper. When I do this, I end up with 5757 features instead of the 6125...