Gasser Elbanna

icon indicating a website link https://gasserelbanna.github.io/

icon location United States icon location PhD Student at Harvard, interested in studying speech processing in the brain using AI models.

Results 3 issues of Gasser Elbanna

add yan 2023 parcellation with kong 17 networks and multiple resolutions.

In this PR, I integrated the yan 2023 homotopic parcellation proposed [here](https://github.com/ThomasYeoLab/CBIG/tree/master/stable_projects/brain_parcellation/Yan2023_homotopic) with multiple resolutions _(from 100 to 1000 parcels)_ matched with Kong 17 networks. _prepare_yan_kong17.py_ follows similar setup as...

Can't reproduce pretraining results for Wav2vec2 using LibriSpeech recipe

11 comment

### Describe the bug Hello, I am pretraining Wav2vec2 following the instructions on this [page](https://github.com/speechbrain/speechbrain/tree/develop/recipes/LibriSpeech/self-supervised-learning/wav2vec2). The pretraining went very smoothly (thank you for that!!), however, when I compared the training...

bug

Multi-GPU issue when pre-training Wav2Vec2

5 comment

### Describe the bug I am trying to train Wav2Vec2 with multi-GPUs (8 A100s). However running the line below leads to a warning and the training freezes after the first...

bug