Integrating Conversational AI Models into Jarvis
================================================

.. _integrating_tlt_trained_models_to_jarvis:

While the Transfer Learning Toolkit is an excellent resource to train and finetune models, 
Jarvis provides resources to deploy those models into scalable services running on GPUs.

Along with the TLT conversational AI package, we provide the following sample resources on `NGC`_ 
to capture the end to end workflow of training a model with TLT and deploying them to Jarvis.

+--------------------------------+--------------------------------------------------+
|  **Conversational AI Task**    |               **Jupyter Notebooks**              |
+================================+==================================================+
| Speech to Text                 | `Speech to Text Notebook`_                       |
+--------------------------------+--------------------------------------------------+
| Speech to Text Citrinet        | `Speech to Text Citrinet Notebook`_              |
+--------------------------------+--------------------------------------------------+
| Question Answering             | `Question Answering Notebook`_                   |
+--------------------------------+--------------------------------------------------+
| Text Classification            | `Text Classification Notebook`_                  |
+--------------------------------+--------------------------------------------------+
| Token Classification           | `Token Classification Notebook`_                 |
+--------------------------------+--------------------------------------------------+
| Punctuation and Capitalization | `Punctuation Capitalization Notebook`_           |
+--------------------------------+--------------------------------------------------+
| Intent and Slot Classification | `Intent Slot Classification Notebook`_           |
+--------------------------------+--------------------------------------------------+

Each sample resouce contain 2 sample notebooks, 

1. To train the respective model using TLT and generate an exported :code:`.ejrvs` 
2. To use this exported :code:`.ejrvs` file and deploy it to Jarvis.

You may find more information about the same in the Jarvis `Documentation`_.

.. _Speech to Text Notebook: https://ngc.nvidia.com/resources/nvidia:tlt-jarvis:speechtotext_notebook
.. _Speech to Text Citrinet Notebook: https://ngc.nvidia.com/resources/nvidia:tlt-jarvis:speechtotext_citrinet_notebook
.. _Question Answering Notebook: https://ngc.nvidia.com/resources/nvidia:tlt-jarvis:questionanswering_notebook
.. _Text Classification Notebook: https://ngc.nvidia.com/resources/nvidia:tlt-jarvis:textclassification_notebook
.. _Token Classification Notebook: https://ngc.nvidia.com/resources/nvidia:tlt-jarvis:tokenclassification_notebook
.. _Punctuation Capitalization Notebook: https://ngc.nvidia.com/resources/nvidia:tlt-jarvis:punctuationcapitalization_notebook
.. _Intent Slot Classification Notebook: https://ngc.nvidia.com/resources/nvidia:tlt-jarvis:intentslotclassification_notebook
.. _`Documentation`: https://docs.nvidia.com/deeplearning/jarvis/user-guide/docs/samples/index.html#model-overview 
.. _`NGC`: https://ngc.nvidia.com