Command-line Clients
====================

A Docker image containing sample command-line drivers for the Jarvis services is available on NGC.
Pull and run the container by using the commands below. The client expects that a Jarvis server is
running with models deployed, and all command-line drivers accept an optional argument to specify
the location of the server. No GPU is required to run the sample clients.

.. prompt:: bash
    :substitutions:

    docker pull nvcr.io/|NgcOrgTeam|/jarvis-clients:|VersionNum|
    docker run -it --rm nvcr.io/|NgcOrgTeam|/jarvis-clients:|VersionNum|


Speech Recognition
------------------
Both binary C++ and Python clients are included in the Docker image with options to do
ASR inference in **streaming** as well as **offline (non-streaming)** mode.

C++ Streaming Example
~~~~~~~~~~~~~~~~~~~~~
Running the C++ ASR streaming client, where ``--audio_file`` is used to specify the
audio file that is to be transcribed.  Other options can be found in
``jarvis_streaming_asr_client.cc``.

.. prompt:: bash

    jarvis_streaming_asr_client --audio_file /work/wav/test/1272-135031-0001.wav

C++ Offline/Batch (non-streaming) Example
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Running the C++ ASR offline client, where ``--audio_file`` is used to specify the
audio file that is to be transcribed.  Other options can be found in 
``jarvis_asr_client.cc``.

.. prompt:: bash

    jarvis_asr_client --audio_file /work/wav/test/1272-135031-0001.wav


Python Streaming Example
~~~~~~~~~~~~~~~~~~~~~~~~
Running the Python ASR streaming client, where ``--input-file`` is used to specify the 
audio file that is to be transcribed.  Other options can be found in
``jarvis_streaming_asr_client.py``.

.. prompt:: bash

   	python jarvis_streaming_asr_client.py --input-file=/work/wav/test/1272-135031-0001.wav

Other Python ASR clients are also available:

#.  ``transcribe_file.py`` transcribes audio files in streaming mode.
#.  ``transcribe_file_offline.py`` transcribes audio files in offline mode.
#.  ``transcribe_file_rt.py`` transcribes audio files while playing back through PyAudio stream.
#.  ``transcribe_mic.py`` transcribes audio from a microphone device.


Natural Language Processing
---------------------------
Both binary C++ and Python clients are included in the Docker image for supported NLP tasks.

C++ NER Example
~~~~~~~~~~~~~~~
Running C++ Token Classification Model (NER) where ``--queries`` is used to specify the 
query file in which to provide token labels for. Other options can be found in 
``jarvis_nlp_classify_tokens.cc``.

.. prompt:: bash

   	jarvis_nlp_classify_tokens --queries=/work/test_files/nlu/queries.txt

C++ QA Example
~~~~~~~~~~~~~~
Running the C++ Question Answering client where ``--questions`` is used to specify the
file containing questions and ``--contexts`` is used to specify the file containing the context
paragraph. Other options can be found in ``jarvis_nlp_qa.cc``.

.. prompt:: bash

   	jarvis_nlp_qa --questions=/work/test_files/nlu/qa_questions.txt --contexts=/work/test_files/nlu/qa_contexts.txt

Python QA Example
~~~~~~~~~~~~~~~~~
Running the Python Question Answering client. Modify ``test_context`` and ``req.query``
in the ``test_qa.py`` script to try different QA examples. 

.. prompt:: bash

    python test_qa.py

C++ Punctuation Example
~~~~~~~~~~~~~~~~~~~~~~~
Running the C++ Punctuation client where ``--queries`` is used to specify the file containing 
inputs to punctuate. Note that, if you want to specify ``--output`` to write output of the 
punctuation model to a file, you need to also specify ``--parallel_requests=1``. 

.. prompt:: bash

    jarvis_nlp_punct --queries=/work/test_files/nlu/punctuation_input.txt


Speech Synthesis
----------------
Binary C++ clients are supported in the Docker image for TTS.

C++ TTS Client Example
~~~~~~~~~~~~~~~~~~~~~~
Running the C++ TTS client where ``--text`` is used to specify the input text for which to
synthesize audio. The output of the client is a ``wav`` file which can be specified by ``--audio_file``. Other options can be found in ``jarvis_tts_client.cc``.

.. prompt:: bash

    jarvis_tts_client --text="I had a dream yesterday."

C++ TTS Performance Client Example
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Running the C++ TTS Performance client which will provide information about latency and
throughput. Options ``--text`` can be used to specify the input text and ``--text_file`` can
be used to specify the file containing multiple text inputs. Other options can be found in 
``jarvis_tts_perf_client.cc``.

.. prompt:: bash

    jarvis_tts_perf_client --text_file=/work/test_files/tts/ljs_audio_text_test_filelist_small.txt

Python Client Examples
~~~~~~~~~~~~~~~~~~~~~~
Two command line clients implemented in Python are provided as an example of how to
interact with the TTS service using the Python API. `talk.py` is an implementation of a client
for performing offline inference, and `talk_stream.py` an implementation using online inference
(with audio being streamed back to the client in chunks).