-
## Goal
Experiment on WhisperVQ model for better result on multilingual. Hypothesis the current codebook is only 512 which is a small space to compress the multilingual capability.
## Learning Goa…
-
Hello,
Thanks for the great paper and releasing the code!
I've been trying to reproduce the numbers shown in Fig4 of the paper where you show the effect of increasing the number of frames comparin…
-
An initial effort has been done to include many models for the modelling and classification task. However, there are several small improvements that could greatly benefit the package.
Hyperparamete…
-
I think it would be informative to consider creating a `cfa-rtgam-pipeline` repository based on [`cfa-epinow2-pipeline`](https://github.com/CDCgov/cfa-epinow2-pipeline) but for the in development `RtG…
-
Please fix the following issues. To test locally, run:
```
pydocstyle path-to-file --count
```
Run this command before and after fixing the errors. This command prints out the number of errors at th…
-
Dear author,
I downloaded your 1-shot tieredImageNet pretrained model and implemented with the default settings (i.e., group=64). However, I can only get 66.80% by averaging 10,000 episodes. Any sugg…
-
Hello,
I've read your paper and have a few questions that I wanted to discuss:
1. In Figure 1 of the paper, pooling is done through token averaging. Have you tried any other pooling methods? I u…
-
```
I had a play around with BEAUTi recently and couldn't help but notice that
discretized branch rates is the default for relaxed clock models. Since we now
have a proper continuous implementation …
-
Hi!
Thank you for providing this useful AutoML package.
In several of the main tree models (e.g. XGBoost 2.0, CatBoost) the regressors support fitting against multiple targets (see [here](http…
-
Thanks for your job! It really help me so much.
It seems that in the deepmind I3D version, they use average pool along the time dimension for the last logits. But in your codes, you use max_pool for …