Soshyant

Greetings, I wanted to know how can we preserve the punctuation?

1- Should I or Can I train a model with Higher sample rate (let's say 48khz) instead of 16khz or this architecture just simply don't support that? I was wondering...

Irregular Loss Pattern ; getting "Loss:NaN"

1

TL;DR: * Encountering frequent NaN values mainly for the Loss, during training with [a large JPN dataset ](https://huggingface.co/datasets/oshizo/japanese-wikipedia-paragraphs)(10.5 million rows). * No such issues with another, albeit [smaller dataset ](https://huggingface.co/datasets/range3/wiki40b-ja)(800,000...

IndexError: index out of range in self | Issue

4

Hi, sounds like the code doesn't work. do you have any suggestions? I followed the exact same steps. used transformers 4.24 and also the most recent version. **torch : 2.1.2**...

The Performance of the new models are bad for specific languages

3

Thank you for creating e2v. how can i access the previous model that could only output a few labels instead of 9? I find this new ckpt (the plus large)...

### ⚠️ Please check that this feature request hasn't been suggested before. - [X] I searched previous [Ideas in Discussions](https://github.com/OpenAccess-AI-Collective/axolotl/discussions/categories/ideas) didn't find any similar feature requests. - [X] I searched...

### Feature request Adding support to ByT5 & UMT5, two popular variants of the T5 Seq2Seq models, would be great. ### Motivation ByT5 is an essential model that outperforms all...