hyunwoo3235 commited on
Commit
33e0a37
โ€ข
1 Parent(s): fdbe804

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -4
README.md CHANGED
@@ -1,9 +1,49 @@
1
  ---
2
  license: apache-2.0
3
  language:
4
- - ko
5
  pipeline_tag: image-to-text
6
  tags:
7
- - trocr
8
- - vision-encoder-decoder
9
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
  language:
4
+ - ko
5
  pipeline_tag: image-to-text
6
  tags:
7
+ - trocr
8
+ - vision-encoder-decoder
9
+ ---
10
+
11
+ # trocr-small-korean
12
+
13
+ ## Model Details
14
+
15
+ TrOCR์€ Encoder-Decoder ๋ชจ๋ธ๋กœ, ์ด๋ฏธ์ง€ ํŠธ๋žœ์Šคํฌ๋จธ ์ธ์ฝ”๋”์™€ ํ…์ŠคํŠธ ํŠธ๋žœ์Šคํฌ๋จธ ๋””์ฝ”๋”๋กœ ์ด๋ฃจ์–ด์ ธ ์žˆ์Šต๋‹ˆ๋‹ค.
16
+ ์ด๋ฏธ์ง€ ์ธ์ฝ”๋”๋Š” DeiT ๊ฐ€์ค‘์น˜๋กœ ์ดˆ๊ธฐํ™”๋˜์—ˆ๊ณ , ํ…์ŠคํŠธ ๋””์ฝ”๋”๋Š” ์ž์ฒด์ ์œผ๋กœ ํ•™์Šตํ•œ RoBERTa ๊ฐ€์ค‘์น˜๋กœ ์ดˆ๊ธฐํ™”๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
17
+
18
+ ์ด ์—ฐ๊ตฌ๋Š” ๊ตฌ๊ธ€์˜ TPU Research Cloud(TRC)๋ฅผ ํ†ตํ•ด ์ง€์›๋ฐ›์€ Cloud TPU๋กœ ํ•™์Šต๋˜์—ˆ์Šต๋‹ˆ๋‹ค.
19
+
20
+ ## How to Get Started with the Model
21
+
22
+ ```python
23
+ import torch
24
+
25
+ from transformers import VisionEncoderDecoderModel
26
+
27
+ model = VisionEncoderDecoderModel.from_pretrained("team-lucid/trocr-small-korean")
28
+
29
+ pixel_values = torch.rand(1, 3, 384, 384)
30
+ generated_ids = model.generate(pixel_values)
31
+ ```
32
+
33
+ ## Training Details
34
+ ### Training Data
35
+
36
+ ํ•ด๋‹น ๋ชจ๋ธ์€ [synthtiger](https://github.com/clovaai/synthtiger)๋กœ ํ•ฉ์„ฑ๋œ 6M๊ฐœ์˜ ์ด๋ฏธ์ง€๋กœ ํ•™์Šต๋˜์—ˆ์Šต๋‹ˆ๋‹ค
37
+
38
+ ### Training Hyperparameters
39
+
40
+ | Hyperparameter | Small |
41
+ |:--------------------|--------:|
42
+ | Warmup Steps | 4,000 |
43
+ | Learning Rates | 1e-4 |
44
+ | Batch Size | 512 |
45
+ | Weight Decay | 0.01 |
46
+ | Max Steps | 500,000 |
47
+ | Learning Rate Decay | 0.1 |
48
+ | \\(Adam\beta_1\\) | 0.9 |
49
+ | \\(Adam\beta_2\\) | 0.98 |