|
Oh, snap, we've been working on importing Gutenburg to LR: https://www.languagereactor.com/m/t_en_- We're ranking them using the download count, and also this prompt to chatGPT (it's primarily for language learners): "Is this text engaging and interesting for a modern reader, someone not into fine literature? Rate the text excellent, good, ok or poor. I don't want crusty, flowery, contorted language, talking about buttons and mannerisms and the hue of the sky etc." Then, we're rewriting the ~1000 most popular books using chatGPT to modernise/simplify the text. Using some markdown as an internal format, drawing from the gutenberg plain text and html formats, this will go to a github repo shortly. There's translations, and then, need to look at current best TTS voices. |
That seems much better for people trying to learn English.
https://standardebooks.org/
They carefully curate and copy-edit their books, and go for quality over quantity. I think that is probably the right choice. We already have free access to an effectively infinite amount of mediocre content on the internet.