DataNexus is a simple to use Python module that you can use in your projects to get transcripts, datasets, etc. The module also allows you to extract character lines from transcripts witch makes it easyer for you to be able to do finetunning of a GPT2 model as an example.

• Downloading of Datasets and Transcripts
• Extract Characters from Transcripts

To get started:

pip install datanexus

⚠️ | Full documenation link to come in the future and the code may be unstable as in testing!

from datanexus import datanexus

datanexus = datanexus()

datasets = datanexus.download_dataset('ironman.txt')
print(datasets)

You will need to create a folder called Models to sucessfully extract the character information

from datanexus import datanexus

character = datanexus.save_character('ironman.txt', 'Tony Stark:', 'Tony.txt')
print(character)

This function will show all of the possible datasets that is usable

from datanexus import datanexus

datasets = datanexus.possible_models()

for dataset in datasets:
    print(dataset)

If you have any question or any issues then feel free to create an issue on Github.

Feel free to join The Workshop discord server and send me a ping (_Ethan_)