-h,       --help          [default] show this help message and exit
    -la,      --list-adapters List graphic adapters and exit
    -gpu,     --use-gpu       The graphic adapter to use for inference
    -t N,     --threads N     [4      ] number of threads to use during computation
    -p N,     --processors N  [1      ] number of processors to use during computation
    -ot N,    --offset-t N    [0      ] time offset in milliseconds
    -on N,    --offset-n N    [0      ] segment index offset
    -d  N,    --duration N    [0      ] duration of audio to process in milliseconds
    -mc N,    --max-context N [-1     ] maximum number of text context tokens to store
    -ml N,    --max-len N     [0      ] maximum segment length in characters
    -wt N,    --word-thold N  [0.01   ] word timestamp probability threshold
    -su,      --speed-up      [false  ] speed up audio by x2 (reduced accuracy)
    -tr,      --translate     [false  ] translate from source language to english
    -di,      --diarize       [false  ] stereo audio diarization
    -otxt,    --output-txt    [false  ] output result in a text file
    -ovtt,    --output-vtt    [false  ] output result in a vtt file
    -osrt,    --output-srt    [false  ] output result in a srt file
    -owts,    --output-words  [false  ] output script for generating karaoke video
    -ps,      --print-special [false  ] print special tokens
    -nc,      --no-colors     [false  ] do not print colors