Amit Moryossef

How about wrapping the `tfds` with a [generic wrapper](https://github.com/sign-language-processing/datasets/blob/master/sign_language_datasets/utils/torch_dataset.py) that makes the data in `torch`? ```python from sign_language_datasets.utils.torch_dataset import TFDSTorchDataset # Fast download and load dataset using TFDS config =...

hmmm if `run_task` can be local, then in theory it can just run on a single machine. I do see one difficulty with that, which is that each task requires...

> Have you made any progress on this? I'm considering using mediapipe keypoints as well I haven't yet attempted an implementation. I think it would be really cool, once I...

I see that you are trying to use this repository with VGT. The `download_lexicon` script does not support any VGT dataset, so to support Flemish, you would have to go...

> hello,I have one problem, look at. > > **_download_lexicon --name --directory _** > > What should I put in "name" and "directory" in this code? the only dataset available...

This is because these values are hardcoded here: https://github.com/sign-language-processing/spoken-to-signed-translation/blob/main/spoken_to_signed/bin.py#L71-L72 We might want to load them dynamically.

This repository allows loading any lexicon. For example, we load the suisse lexicon, but any lexicon can be added. sign.mt is an independent website, that uses this project, but with...

In `sign/translate`, the backend for the `spoken-text-to-pose` is closed source for multiple reasons. Ideally, everything will work client side only, but this is not yet the case.

Among other things, yes.

Using the `spacylemma` module or `simple` module, you can lemmatize English text into pseudo-glosses. If you'd like the `rules` module to work for `ASL`, you would have to implement the...