| r""" | |
| Atienza, Rowel. "Vision Transformer for Fast and Efficient Scene Text Recognition." | |
| In International Conference on Document Analysis and Recognition (ICDAR). 2021. | |
| https://arxiv.org/abs/2105.08582 | |
| All source files, except `system.py`, are based on the implementation listed below, | |
| and hence are released under the license of the original. | |
| Source: https://github.com/roatienza/deep-text-recognition-benchmark | |
| License: Apache License 2.0 (see LICENSE file in project root) | |
| """ | |