Nirant

Can you please raise a PR with the `fastapi`? Would like to port to fastAPI from flask is possible. cc @meghanabhange as the author+maintainer

Could you please share the steps before this line? It seems like you are trying a different model in some manner, this is indicated by the difference in dimensions: ```python...

Hey @008karan, as a solo dev - I don't have the bandwidth to support this older version while building out newer version. If you'd be so kind to have some...

fastai has changed both the language model API and data block API. It would be great to train a new Hindi language model. Refer fastai docs here: https://docs.fast.ai/text.learner.html#language_model_learner The data...

The training (and/or validation) loss and perplexity are calculated during model training as shown in the notebook. This is done by fastai implementation of metrics via hooks. We can repeat...

I had stumbled across the [Story Cloze dataset](http://cs.rochester.edu/nlp/rocstories/). Is that a reasonable starting point?

Would it be worthwhile to have demo "applets" which would integrate with more low code tools like Streamlit, Retool, and AppSmith? This approach could help Obsei get more users without...

Not in the sense of using Obsei, but for showing the final output or a summary of the same. E.g. in the example above, Slack is where you finally publish...

From the Official README: > `XLNet-Large, Cased` model: 24-layers, 1024-hidden, 16-heads Also mentioned, similar model size at `BERT-Large, cased` which is **340M parameters**. Source: [Official BERT README](https://github.com/google-research/bert#bert).

In the same vein, maybe forced predictions should not be called `Real`? That makes it sound like Ground Truth - which is misleading. ```Real: 3``` --> ```Forced Prediction: 3``` This...