Unable to inference infographicVQA task

I am trying to run the inference of the model for infographic vqa task. The instruction mention the cli command for a dummy task and is as follows:
python -m pix2struct.example_inference \
--gin_search_paths="pix2struct/configs" \
--gin_file=models/pix2struct.gin \
--gin_file=runs/inference.gin \
--gin_file=sizes/base.gin \
--gin.MIXTURE_OR_TASK_NAME="'dummy_pix2struct'" \
--gin.TASK_FEATURE_LENGTHS="{'inputs': 2048, 'targets': 128}" \
--gin.BATCH_SIZE=1 \
--gin.CHECKPOINT_PATH="'gs://pix2struct-data/textcaps_base/checkpoint_280400'" \
--image=$HOME/test_image.jpg

I have added the task task name, check point and text prompt for vqa task. But they are not in accordance to the requirement. Please provide a correct set of input values to perform the inference for the task.

python -m pix2struct.example_inference \
--gin_search_paths="pix2struct/configs" \
--gin_file=models/pix2struct.gin \
--gin_file=runs/inference.gin \
--gin_file=sizes/base.gin \
--gin.MIXTURE_OR_TASK_NAME="InfographicVQA" \
--gin.TASK_FEATURE_LENGTHS="{'inputs': 2048, 'targets': 128}" \
--gin.BATCH_SIZE=1 \
--gin.CHECKPOINT_PATH="gs://pix2struct-data/infographicvqa_large/checkpoint_182000" \
--image="my_input_image.jpeg" \
--text="What is written on the image of the calendar ?"