This commit is mainly for two new models and their accompanying datases.
City name model: one for generating Dutch plaatsnamen (I scraped this data from Wikipedia for a very similar project a few months ago, so I am excited to reuse it here!)
Both models can be loaded, for the last name model a new vocabulary object was made (without numbers, including some special alphabetic characters).
I moved the actual code for training a model to a file in the root directory called train_wrapper.py.
Let me know if there is a better directory to put the training file in, without needing import hacks like sys.path.append(..)....
This commit is mainly for two new models and their accompanying datases.
Both models can be loaded, for the last name model a new vocabulary object was made (without numbers, including some special alphabetic characters).
I moved the actual code for training a model to a file in the root directory called train_wrapper.py. Let me know if there is a better directory to put the training file in, without needing import hacks like
sys.path.append(..)....