Download speeds very slow on initial startup

[Ori-Pixel]

Hi, the download seems to take 4 hours for the bert .model files from the server end. Is there a way to wget or curl them into a directory? Also, if one terminates the program, the files are still partially written in and cause an unzipping error in pytorch. Is there a plan to mitigate this in the future with tempfile downloads?

minimal example:

import booknlp
from booknlp.booknlp import BookNLP
import spacy
spacy.load('en_core_web_sm')
model_params = {
    "pipeline": "entity,quote,supersense,event,coref",
    "model": "big"
}

booknlp = BookNLP("en", model_params)

# Input file to process
input_file = "input_dir/bartleby.txt"

# Output directory to store resulting files in
output_directory = "output_dir/bartleby/"

# File within this directory will be named ${book_id}.entities, ${book_id}.tokens, etc.
book_id = "bartleby"

booknlp.process(input_file, output_directory, book_id)

https://i.imgur.com/FZIqNsC.png