How do you use TensorFlowASR deepspeech2?

Question

Here is the documentation:

See python examples/deepspeech2/train_*.py --help

Here is the help:

python examples/deepspeech2/test.py --help
2023-05-29 10:14:55.122077: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
INFO: Showing help with the command 'test.py -- --help'.

NAME
    test.py

SYNOPSIS
    test.py <flags>

FLAGS
    --config=CONFIG
        Type: str
        Default: '.../TensorFlowASR/examples/deepspeech2/config.yml'
    --saved=SAVED
        Type: Optional[str]
        Default: None
    --mxp=MXP
        Type: bool
        Default: False
    --bs=BS
        Type: Optional[int]
        Default: None
    --sentence_piece=SENTENCE_PIECE
        Type: bool
        Default: False
    --subwords=SUBWORDS
        Type: bool
        Default: False
    --device=DEVICE
        Type: int
        Default: 0
    --cpu=CPU

Questions:

1. What does this script do? What is an example of running it to get some interesting output?

2. How can I use this script (or a related script) to actually transcribe some audio, preferably in real time?