v0.1 (5/6/2024)
First working release.
Notable features:
- image-to-text conversion of news headlines created with Snapchat (via Tesseract-based OCR)
- news headline database creation/handling with sqlite
- functions to query the database for search terms, print a random headline, print the total number of headlines
- via the trigrams subcommand:
- function to train a trigram language model and synthesize a new headline based on the corpus generated from the database
- via the tokenizer subcommand:
- function to create a secondary database for storing counts of individual tokens in the database
- function to query the database for a given token and print its count
- via the visualizer subcommand:
- function to display a word cloud of the most frequently occurring terms in the database