search

apeled / TLDhubeR

MIT License
4 stars 1 forks source link

TODO ISSUE #2

Open MarkUnivWash opened 5 months ago

MarkUnivWash commented 5 months ago

Setup Azure Space, Blobs, Authentication, and Model Endpoint Scrape YouTube for Transcripts Train Model on Andrew Huberman's Voice

apeled commented 5 months ago

Need to also reformat/find solutions to store the dataframe that was scraped. Excel has a max cell length of 32,760 characters so the current excel file has incomplete transcripts. Need to also reformat the transcript format to make it easier for model training