Lakshmi Bashyam

Hello, I seem to have the same issue while getting the speech segment. This occurs only when I use cuda for VAD. This is my code, ``` VAD = VAD.from_hparams(...

Thank you for the constructive discussion and your input on this PR. I appreciate your engagement and collaboration. I will be going on maternity leave soon and will be back...

> Thanks for your insight @mfakaehler and @katjakon ! I agree that making it possible to provide a separate validation data set during XTransformer training makes sense. But the CLI...

> A good starting point might be the **hyperparameters used in the [original paper](https://arxiv.org/abs/2110.00685)**. They can be found [here](https://github.com/amzn/pecos/tree/mainline/examples/xr-transformer-neurips21). Different settings were used for different datasets. Regarding the parameter configuration:...

The **PECOS TF-IDF vectorizer** has a significant limitation: it does not allow the use of custom tokenizers. Instead, it relies exclusively on its built-in tokenizer. ## Technical Details The core...

@mfakaehler You’re correct — PECOS hasn’t yet been updated to work with the latest Transformers versions. I’ve also opened an issue with the PECOS team about this: https://github.com/amzn/pecos/issues/311 Currently, **PECOS...

@osma Yeah, I’m with you on this. For now I’ll see if I can update the dependencies without conflicts and send a PR over to the PECOS team. On the...