Initial commit of weights

README.md

@@ -0,0 +1,38 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- image-to-text
+---
+
+# ViTSTR small v1.0
+
+ViTSTR model pre-trained on various real [STR datasets](https://github.com/baudm/parseq/blob/main/Datasets.md) at image size 128x32 with a patch size of 8x4.
+
+Disclaimer: this model card was not written by the original author.
+
+## Model description
+
+*TODO*
+
+## Intended uses & limitations
+
+You can use the model for STR on images containing Latin characters (62 case-sensitive alphanumeric + 32 punctuation marks).
+
+### How to use
+
+*TODO*
+
+### BibTeX entry and citation info
+
+```bibtex
+@InProceedings{atienza2021vision,
+  title={Vision transformer for fast and efficient scene text recognition},
+  author={Atienza, Rowel},
+  booktitle={International Conference on Document Analysis and Recognition},
+  pages={319--334},
+  year={2021},
+  organization={Springer}
+}
+```

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d0fcf4ed83d4af268c6b2371d20afe15a6e78aae619f32bc193636ef6ede30
+size 85725649

torchscript_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81f112ead1b32cec66fe691d5141c7d244f1280defe5d5109303802be383fd4
+size 85739038