Kenenbek R
Kenenbek R
### Description I use just some input activations, one SelfAttention layer and `n_heads=2`, but my code breaks. However, when I set `n_heads=1`, everything works fine. ### Environment information ``` OS:...
When I read docs here https://trax-ml.readthedocs.io/en/latest/trax.models.html#trax.models.reformer.reformer.EncoderDecoderBlock I see a name `EncoderDecoderBlock`, but later a description of it: > Reversible transformer decoder layer. Is it a typo?
I built an image in this [directory](https://github.com/jupyterhub/jupyterhub-deploy-docker/tree/master/examples/custom-notebook-server): `docker build -t custom-notebook-server . ` Then I tried to run it: `docker run --rm -it custom-notebook-server` But it gives me an error:...
https://github.com/toddwildey/shors-python/blob/a7e47d6ba59dcd9d8b9bd37e8e34e8c7cac1b182/shors.py#L243
### Tested versions pyannote.audio-4.0.1 pyannote.audio-4.0.2 ### System information Description: Ubuntu 24.04.3 LTS Release: 24.04 ### Issue description I used a pyannote on a five mins long audio. Segmentation, speaker_counting take...