You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

67 lines
1.9 KiB
Plaintext

# OuNuPo Make
Software experiments for the OuNuPo bookscanner, part of Special Issue 5
https://issue.xpub.nl/05/
https://xpub.nl/
## License
## Authors
Natasha Berting, Angeliki Diakrousi, Joca van der Horst, Alexander Roidl, Alice Strete and Zalán Szakács.
## Clone Repository
`git clone https://git.xpub.nl/repos/OuNuPo-make.git`
## General depencies
* Python3
* GNU make
* Python3 NLTK `pip3 install nltk`
* NLTK English Corpus:
* run NLTK downloader `python -m nltk.downloader`
* select menu "Corpora"
* select "stopwords"
* "Dowload"
# Make commands
## N+7 (example) Author
Description: Replaces every word with the 7th next word in a dictionary.
run: `make N+7`
Specific Dependencies:
* a
* b
* c
## Sitting inside a pocket(sphinx): Angeliki
Description: Speech recognition feedback loops using the first sentence of a scanned text as input
run: `make ttssr-human-only`
Specific Dependencies:
* [pocketsphinx](https://github.com/bambocher/pocketsphinx-python) `sudo pip3 install pocketsphinx` ---> FOLLOW THIS EXAMPLE
* SpeechRecognition 3.8.1
* PyAudio
## Reading the Structure: Joca
Description: Uses OCR'ed text as an input, labels each word for Part-of-Speech, stopwords and sentiment. Then it generates a reading interface
where words with a specific label are hidden. Output can be saved as poster, or exported as json featuring the full data set.
run: `make output/reading_structure/index.html`
Specific Dependencies:
* nltk (http://www.nltk.org/install.html)
* nltk.tokenize.punkt, ne_chunk, pos_tag, word_tokenize, sentiment.vader (https://www.nltk.org/data.html)
* weasyprint (http://weasyprint.readthedocs.io/en/latest/install.html)
* jinja2 (http://jinja.pocoo.org/docs/2.10/intro/#installation)
* font: PT Sans (os font https://www.fontsquirrel.com/fonts/pt-serif)
* font: Ubuntu Mono (os font https://www.fontsquirrel.com/fonts/ubuntu-mono)