Amit Moryossef

Results 178 issues of Amit Moryossef

Currently fails due to `canvas` being referenced in the holistic source code - issue https://github.com/google/mediapipe/issues/2506 Fixes #24

## Expected Behavior Material Icons should only load used icons ## Actual Behavior The Material Icons font is 100kb(!), loads all fonts. ## Steps to fix? Use https://fonttools.readthedocs.io/en/latest/subset/index.html to subset...

enhancement

Holistic doesn't support iOS safari - https://github.com/google/mediapipe/issues/1427 Once support exists, re-consider this change, as it has performance issues: https://github.com/sign-language-processing/playground/commit/f43dce163e71702793a4eec5fc47f98c939cd80c#diff-234795a41fd0cddbe6708c29494ba2caf76de81e3fc82c0294394dce2ec968dcR52-R59

bug
signed-to-spoken

## Expected Behavior Holistic should not block the main thread ## Actual Behavior It does block the main thread. ## Ways to fix: I set up a branch that isn't...

enhancement
signed-to-spoken

Add a "Detect Language" to signed-to-spoken language translation, which identifies the signed language based on a sequence of poses.

enhancement
help wanted
signed-to-spoken

The tab order is not great, I assume some other things as well. Guide: https://web.dev/accessible/

enhancement
good first issue
help wanted

After text is translated to SignWriting, the SignWriting should be translated to a sequence of poses. This sequence should be then blobed, and created as a resource ```js const blob...

enhancement
signwriting
spoken-to-signed

In addition to the SkeletonPoseViewer and HumanPoseViewer, support an AvatarPoseViewer. ![image](https://user-images.githubusercontent.com/5757359/195430916-4281a77d-8457-425c-a2a8-9b396330d8bb.png) The current avatar does not move, as the only implementation I wrote does not perform amazing: https://www.youtube.com/watch?v=TyJuU9_GOaw Since then,...

enhancement
spoken-to-signed

fixes #102 (tested for my training, this works) One thing that is a bit ugly: To make it so `marian` early stops on the correct metric, I added it to...

In the train file, we save the `final` model always to be the `chrf` model. https://github.com/mozilla/firefox-translations-training/blob/main/pipeline/train/train.sh#L53-L54 This makes it so the model has the wrong name. The pipeline wants: https://github.com/mozilla/firefox-translations-training/blob/main/Snakefile#L433...