gg4ever
/

trOCR-final

vision-encoder-decoder

image-text-to-text

Inference Endpoints

Model card Files Files and versions Community

gg4ever commited on Sep 2, 2023

Commit

2fc9213

·

1 Parent(s): 6628dd5

Update README.md

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -44,9 +44,9 @@ print(generated_text)
 ## Training Details
 ### Training Data
-100k words generated by TextRecognitionDataGenerator(trdg) : https://github.com/Belval/TextRecognitionDataGenerator/blob/master/trdg/run.py
-120k words from AI-hub OCR words dataset : https://aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&dataSetSn=81
 ### Training Hyperparameters
@@ -59,5 +59,6 @@ print(generated_text)
 |num_train_epochs|2|
 |fp16|True|
 |learning_rate|4e-5|
-|warmup_steps|2000|
 |weight_decay|0.01|

 ## Training Details
 ### Training Data
+1M words generated by TextRecognitionDataGenerator(trdg) : https://github.com/Belval/TextRecognitionDataGenerator/blob/master/trdg/run.py
+1.1M words from AI-hub OCR words dataset : https://aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&dataSetSn=81
 ### Training Hyperparameters
 |num_train_epochs|2|
 |fp16|True|
 |learning_rate|4e-5|
+|eval_stept|10000|
+|warmup_steps|20000|
 |weight_decay|0.01|