Handwriting Model

NOTE:

This is repository is archived. I will no longer update or change the code.

The code works but doesn't produce good results. Use at your own risk.

Implementation of a model for Handwriting Synthesis using
a Long Short-Term Memory recurrent neural networks in PyTorch.

Based on the Handwriting Synthesis section of Generating Sequences With Recurrent Neural Networks
by Alex Graves.

Dataset

The dataset used to train this neural network is the IAM On-Line Handwriting Database.
In order to train this network you have to register then download the following files:

• lineStrokes-all.tar.gz
• ascii-all.tar.gz

Put both of them inside the data directory.

Usage

Create virtual environment and install packages:

python -m venv venv
source venv/bin/activate
pip install -e .

Then execute the following to train the model:

python -m handwriting_generator

See the main script's help text for more information:

python -m handwriting_generator --help