Joshua Lochner

I opened a feature request to Optimum quite some time ago: https://github.com/huggingface/optimum/issues/1214. Adding support there is a prerequisite for Transformers.js support :)

Hi there 👋 Can you provide the error logs you get (+ jest version)? We use jest for unit tests and do not have any issues with it.

Thanks! Will merge after tests pass. By the way, do you have an example of a whisper model which such tokens? Might be good to add a test.

We could probably use the time precision (0.02) to calculate the offset: 30/0.02 + 1 = 1501 tokens (50364 -> 51864). Another fix is to simply update the tokenizer.json. Also,...

Thanks for this! This is exactly what I was planning to do for v3. Can you give the model id of the processor/tokenizer you are loading so I can add...

Good spot! Feel free to submit a PR for this. Thanks! 🤗

Here we go: https://github.com/xenova/transformers.js/pull/795. + list of converted models: https://huggingface.co/models?library=transformers.js&other=decision_transformer&sort=trending I will add example Transformers.js code now too. I'll also look at the model you linked.

Hi there 👋 That's exactly correct! Like the python library, we first look for the model locally before attempting to download the model from the Hugging Face Hub. If the...

Hi there 👋 This library serves as a JavaScript port of the Python [transformers](https://github.com/huggingface/transformers) library, so if you know of a model where you can do this, we can certainly...

You can specify `model_file_name` as one of the options in `.from_pretrained(model_id, { model_file_name: 'model' }` :) Although, do note that the weights I uploaded only work for Transformers.js v3 (unless...