Basic usage

pip install rhymediscovery

>>> from rhymediscovery import find_schemes
>>> find_schemes.find_schemes([['herz', 'welt', 'geld', 'schmerz'], ...])
[(('herz', 'welt', 'geld', 'schmerz'), (1, 2, 1, 2)), ...]

Command line

The command line tool find_schemes expects a file formatted like the .pgold files in the rhymedata corpus. A sample file can be found here in the repo.

To demonstrate the tool, we clone the rhymedata corpus:

git clone https://github.com/sravanareddy/rhymedata.git

Then we run:

find_schemes rhymedata/english_gold/1415.pgold 1415.out

The 1415.pgold file from the corpus has been manually annotated with the correct rhyme schemes. Thus we can evaluate our result file using:

evaluate_schemes 1415.out rhymedata/english_gold/1415.pgold

Credits

This package implements the following paper:

• Sravana Reddy and Kevin Knight. “Unsupervised discovery of rhyme schemes.” Proceedings of ACL 2011. (pdf)

It is a fork of the reference implementation by @sravanareddy which is available in its original form here.