Update README.md

README.md

@@ -1,3 +1,39 @@
 ---
 license: apache-2.0
----
+pipeline_tag: image-to-text
+---
+
+该模型为中英文本混合公式与表格LaTeX OCR，详见：https://arxiv.org/abs/2406.17148。
+This model is designed for mixed Chinese-English text, formula, and table LaTeX OCR. For more details, please refer to: https://arxiv.org/abs/2406.17148.
+
+# 使用方法：
+```python
+from transformers import AutoTokenizer, VisionEncoderDecoderModel, AutoImageProcessor
+from PIL import Image
+import requests
+
+feature_extractor = AutoImageProcessor.from_pretrained("lrqlrqlrq/MixTex_Tiny_ZhEn_Latex_Math_OCR")
+tokenizer = AutoTokenizer.from_pretrained("lrqlrqlrq/MixTex_Tiny_ZhEn_Latex_Math_OCR", max_len=296)
+model = VisionEncoderDecoderModel.from_pretrained("lrqlrqlrq/MixTex_Tiny_ZhEn_Latex_Math_OCR")
+
+imgen = Image.open(requests.get('https://cdn-uploads.huggingface.co/production/uploads/62dbaade36292040577d2d4f/eOAym7FZDsjic_8ptsC-H.png', stream=True).raw)
+#imgzh = Image.open(requests.get('https://cdn-uploads.huggingface.co/production/uploads/62dbaade36292040577d2d4f/m-oVg8dsQbQZ1fDWbwKtO.png', stream=True).raw)
+print(tokenizer.decode(model.generate(feature_extractor(imgen, return_tensors="pt").pixel_values)[0]).replace('\\[','\\begin{align*}').replace('\\]','\\end{align*}'))
+```
+
+# 补充：
+建议图片尺寸：大约 (400, 500), (H, W)。
+建议输出字数：大约100－300个tokens。
+Latex 环境：
+```
+\usepackage{amssymb}
+\usepackage{amsmath}
+\usepackage{stmaryrd}
+\usepackage{color}
+```
+# 样例：
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62dbaade36292040577d2d4f/eOAym7FZDsjic_8ptsC-H.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62dbaade36292040577d2d4f/m-oVg8dsQbQZ1fDWbwKtO.png)
+