Processing Time Too much slow in NLP Bert Module

  bert-language-model, nlp, python

I am a beginner in python and NLP I have a file that contains a module.
When I give question and answer_text to the module it returns an answer to the question using nlp but the processing time is very large about 15-20 minutes.
Is there a hardware problem or function optimation?

import torch

from transformers import BertForQuestionAnswering

def find_answer(question,answer_text):
    model = BertForQuestionAnswering.from_pretrained('bert-large-uncased-whole-word-masking-finetuned-squad')
    from transformers import BertTokenizer
    tokenizer = BertTokenizer.from_pretrained('bert-large-uncased-whole-word-masking-finetuned-squad')
    input_ids = tokenizer.encode(question, answer_text)
    tokens = tokenizer.convert_ids_to_tokens(input_ids)
    # Search the input_ids for the first instance of the `[SEP]` token.
    sep_index = input_ids.index(tokenizer.sep_token_id)
    # The number of segment A tokens includes the [SEP] token istelf.
    num_seg_a = sep_index + 1
    # The remainder are segment B.
    num_seg_b = len(input_ids) - num_seg_a
    # Construct the list of 0s and 1s.
    segment_ids = [0] * num_seg_a + [1] * num_seg_b
    # There should be a segment_id for every input token.
    assert len(segment_ids) == len(input_ids)
    # Run our example through the model.
    outputs = model(torch.tensor([input_ids]),  # The tokens representing our input text.
                    # The segment IDs to differentiate question from answer_text
    start_scores = outputs.start_logits
    end_scores = outputs.end_logits
    # Find the tokens with the highest `start` and `end` scores.
    answer_start = torch.argmax(start_scores)
    answer_end = torch.argmax(end_scores)
    # Combine the tokens in the answer and print it out.
    answer = ' '.join(tokens[answer_start:answer_end + 1])
    return answer

Source: Python Questions