Update README.md
Browse files
README.md
CHANGED
@@ -38,6 +38,14 @@ This model could be used to read labels with printed text.
|
|
38 |
|
39 |
Here is the link to the dataset that I used for this model: https://www.kaggle.com/datasets/ravi02516/20k-synthetic-ocr-dataset
|
40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
## Training procedure
|
42 |
|
43 |
### Training hyperparameters
|
@@ -64,8 +72,6 @@ CER = 0.003 (Actually, 0.002896524170994806)
|
|
64 |
|
65 |
*Note: Please make sure to give proper credit to the owner(s) of the data and developers of the model (microsoft/trocr-base-printed).
|
66 |
|
67 |
-
|
68 |
-
|
69 |
### Model Checkpoint
|
70 |
@misc{li2021trocr, title={TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models}, author={Minghao Li and Tengchao Lv and Lei Cui and Yijuan Lu and Dinei Florencio and Cha Zhang and Zhoujun Li and Furu Wei}, year={2021}, eprint={2109.10282}, archivePrefix={arXiv}, primaryClass={cs.CL}}
|
71 |
|
|
|
38 |
|
39 |
Here is the link to the dataset that I used for this model: https://www.kaggle.com/datasets/ravi02516/20k-synthetic-ocr-dataset
|
40 |
|
41 |
+
_Character Length for Training Dataset:_
|
42 |
+
|
43 |
+
![Input Character Length for Training Dataset](https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/raw/main/Optical%20Character%20Recognition%20(OCR)/20%2C000%20Synthetic%20Samples%20Dataset/Images/Input%20Character%20Length%20Distribution%20for%20Training%20Dataset.png)
|
44 |
+
|
45 |
+
_Character Length for Evaluation Dataset:_
|
46 |
+
|
47 |
+
![Input Character Length for Evaluation Dataset](https://github.com/DunnBC22/Vision_Audio_and_Multimodal_Projects/raw/main/Optical%20Character%20Recognition%20(OCR)/20%2C000%20Synthetic%20Samples%20Dataset/Images/Input%20Characgter%20Length%20Distribution%20for%20Evaluation%20Dataset.png)
|
48 |
+
|
49 |
## Training procedure
|
50 |
|
51 |
### Training hyperparameters
|
|
|
72 |
|
73 |
*Note: Please make sure to give proper credit to the owner(s) of the data and developers of the model (microsoft/trocr-base-printed).
|
74 |
|
|
|
|
|
75 |
### Model Checkpoint
|
76 |
@misc{li2021trocr, title={TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models}, author={Minghao Li and Tengchao Lv and Lei Cui and Yijuan Lu and Dinei Florencio and Cha Zhang and Zhoujun Li and Furu Wei}, year={2021}, eprint={2109.10282}, archivePrefix={arXiv}, primaryClass={cs.CL}}
|
77 |
|