chunked/nltk_chunking/_add_new_pipeline/chunk_24.txt

It's also relatively common to support many different types
of arguments for ease of use (audio files, which can be filenames, URLs or pure bytes)
Adding it to the list of supported tasks
To register your new-task to the list of supported tasks, you have to add it to the PIPELINE_REGISTRY:
thon
from transformers.pipelines import PIPELINE_REGISTRY
PIPELINE_REGISTRY.register_pipeline(
    "new-task",
    pipeline_class=MyPipeline,
    pt_model=AutoModelForSequenceClassification,
)

You can specify a default model if you want, in which case it should come with a specific revision (which can be the name of a branch or a commit hash, here we took "abcdef") as well as the type:
python
PIPELINE_REGISTRY.register_pipeline(
    "new-task",
    pipeline_class=MyPipeline,
    pt_model=AutoModelForSequenceClassification,
    default={"pt": ("user/awesome_model", "abcdef")},
    type="text",  # current support type: text, audio, image, multimodal
)
Share your pipeline on the Hub
To share your custom pipeline on the Hub, you just have to save the custom code of your Pipeline subclass in a
python file.