handler.py

from typing import Dict, List, Any
from transformers import pipeline

class EndpointHandler():
    def __init__(self, path=""):
        self.pipeline = pipeline("automatic-speech-recognition",
                                 model=path, 
                                 chunk_length_s = 30 , 
                                 stride_length_s = (3, 0), 
                                 generate_kwargs = {"language":"pt"} , 
                                 device = 0
                                )

    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
        """
       data args:
            inputs (:obj: `str`)
            date (:obj: `str`)
      Return:
            A :obj:`list` | `dict`: will be serialized and returned
        """
        # get inputs
        inputs = data.pop("inputs",data)
        # run normal prediction
        prediction = self.pipeline(inputs)
        return prediction