Dmitry Kurtaev

Hi! Just wanted to ask if you have some comments here.

@dakshvar22, Sure, sorry for not complete description. TensorFlow backend means default backend for lm_featurizer models from HuggingFace (which if TensorFlow). So config is just ``` language: en pipeline: - name:...

Hi, @dakshvar22. Thanks for help! I used the following script to measure `process` efficiency: Script ```python import time import logging import numpy as np from rasa.shared.nlu.training_data.loading import load_data from rasa.nlu.featurizers.dense_featurizer.lm_featurizer...

@dakshvar22, indeed there is a difference in TensorFlow numbers. Rebased the changes to `2.7.x` branch: https://github.com/dkurt/rasa/tree/2.7.x_openvino Adopted script ```python import time import logging import numpy as np from rasa.shared.nlu.training_data.loading import...

@dakshvar22, the models can be generated in runtime by the following method (already a part of PR): Conversion code ```python def _load_model(self, input_ids: np.ndarray, attention_mask: np.ndarray) -> None: # Serialize...

@dakshvar22, did the following changes: * Models now converted in runtime with no external reference to custom hub * Once converted, OpenVINO models are saved in common cache * Skip...

@dakshvar22, yes, completely! Do you think I need to put this summary to `changelog/9826.feature.md` or `docs/docs/openvino-backend.mdx`?

Hi! Do you think it might reduce maintenance effort and help with integration decision if we wrap OpenVINO related code into a separate package? In example, like Hugging Face's [Optimum](https://github.com/huggingface/optimum)...

Hi, @jupyterjazz! No worries :) I have opened a PR which demonstrates how we can move OpenVINO related code to a separate package: https://github.com/dkurt/rasa/pull/5. > 1. how do you imagine...

@dakshvar22, @jupyterjazz, Good news! Reproduced the same experiment as https://github.com/RasaHQ/rasa/pull/9826#issuecomment-966051532 but with coming OpenVINO release (2022.1). It will propose a dynamism feature which allows process variable input sizes. So parameter...