Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.00051 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908292387700736 |
|---|---|
| author | Greydanus, Sam Wimpee, Zachary |
| author_facet | Greydanus, Sam Wimpee, Zachary |
| contents | Transformers trained on tokenized text, audio, and images can generate high-quality autoregressive samples. But handwriting data, represented as sequences of pen coordinates, remains underexplored. We introduce a novel tokenization scheme that converts pen stroke offsets to polar coordinates, discretizes them into bins, and then turns them into sequences of tokens with which to train a standard GPT model. This allows us to capture complex stroke distributions without using any specialized architectures (eg. the mixture density network or the self-advancing ASCII attention head from Graves 2014). With just 3,500 handwritten words and a few simple data augmentations, we are able to train a model that can generate realistic cursive handwriting. Our approach is simpler and more performant than previous RNN-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00051 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Cursive Transformer Greydanus, Sam Wimpee, Zachary Machine Learning Artificial Intelligence Computation and Language Transformers trained on tokenized text, audio, and images can generate high-quality autoregressive samples. But handwriting data, represented as sequences of pen coordinates, remains underexplored. We introduce a novel tokenization scheme that converts pen stroke offsets to polar coordinates, discretizes them into bins, and then turns them into sequences of tokens with which to train a standard GPT model. This allows us to capture complex stroke distributions without using any specialized architectures (eg. the mixture density network or the self-advancing ASCII attention head from Graves 2014). With just 3,500 handwritten words and a few simple data augmentations, we are able to train a model that can generate realistic cursive handwriting. Our approach is simpler and more performant than previous RNN-based methods. |
| title | The Cursive Transformer |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2504.00051 |