Stephen Fernandes
Stephen Fernandes
hey there, by any chance how could i find the implementation of "exponential smoothed weighting of the data", i need to implement this in my mT5 pre-training. couldn't find it...
### Link _No response_ ### Description Hey there, I have used seqio to get a well distributed mixture of samples from multiple dataset. However the resultant output from seqio is...
hey do you happend to know how does pytorch pad sentence? i used your implementation and tried to decode the processed input using the vocab.itos and found that padding is...
hey Great work on updating the torchtext code, sadly i tried to build torchtext from source as you instructed from the official repo. but i wasn't able to build from...
Hey Ben this isn't an issue with your code. It's just a simple beginner in PyTorch NLP asking you out on how to use the nightly torchtext . I have...
how to pretrain mDeBERTa base and small on a custom dataset ? How to structure the Multilingual lingual dataset. I am planning to pretrain mDEBERTa specifically on multiple Indian Languages....
## searching the ideal torchtext pipeline **Description** hey there, so ive been using the legacy version of torchtext for quite sometime as it provides easier ways to load custom dataset...
Hi there, I am planning to finetune XLS-R on multiple decoder heads like langauge detection, ASR, speech to IPA, gender identification etc do you know any XLS-R, WavLM or any...
Hey there, So ive been using pysbd to detect boundries in hindi and marathi language and then save the same data rearranged from a paragraph to one sentence boundry per...
Hey there, thanks for providing such an marvelous tool. I've been trying to find a way to interpret ASR models using Shap, but couldn't actually find anything in the docs....