Amit Moryossef
Amit Moryossef
Hi! Are there plans on the pipeline to make the decoder able to generate multiple tokens, to perform CSLR?
Very nice repo and documentation! I think this repository can benefit from using https://github.com/sign-language-processing/datasets as data loaders. It is fast, consistent across datasets, and allows loading videos / poses from...
Seems like for pose data you are using `pkl` and `h5`. Also, that you have a custom [mediapipe holistic script ](https://github.com/AI4Bharat/OpenHands/blob/main/scripts/mediapipe_extract.py) Personally I believe it would be more shareable, and...
It's me again, I've been trying to get this repository to work for over two years now. This project still seems like the best machine translation project to train models...
This is a "support" request rather than a bug or a feature. ---- ## Idea I have a "video" sequence that is represented as skeletal poses rather than video frames....
I was looking for a drop in replacement for torch's TransformerEncoder: ```py nn.TransformerEncoder( nn.TransformerEncoderLayer(d_model=hidden_dim, nhead=nhead, dim_feedforward=dim_feedforward, batch_first=True), num_layers=num_layers ) ``` And while this repo does offer a `LocalTransformer` (#10), the...
Frameworks such as Mediapipe or OpenPose are used to extract skeletal keypoints from images. Unfortunately, the results are inconsistent and somewhat jittery when trying to extract poses from consecutive frames....
Continuation of #6 We should consider using SSML for describing the desired output more carefully https://cloud.google.com/text-to-speech/docs/ssml
We now use the improved [`pose-to-video`](https://github.com/sign-language-processing/pose-to-video) based on diffusion models. We start with a paragraph in German, translate it to German Sign Language: > Das Alte Museum wurde 1830 als...
the BSL videos include a long leading pause, which make concatenating them less nice compared to ASL for example https://sign.mt/?text=1%202%203%204%205&sil=bfi&spl=en | BSL | ASL | | --- | --- |...