priyank-m commited on
Commit
04c5ff2
·
1 Parent(s): 6b7803f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +18 -1
README.md CHANGED
@@ -10,4 +10,21 @@ datasets:
10
  - priyank-m/text_recognition_en_zh_clean
11
  metrics:
12
  - cer
13
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  - priyank-m/text_recognition_en_zh_clean
11
  metrics:
12
  - cer
13
+ ---
14
+
15
+ Multilingual OCR (mOCR) is a VisionEncoderDecoder model based on the concept of TrOCR for English and Chinese document text-recognition.
16
+ It uses a pre-trained Vision encoder and a pre-trained Language decoder model.
17
+
18
+ Encoder model used: facebook/vit-mae-large
19
+ Decoder model used: xlm-roberta-base
20
+
21
+
22
+
23
+
24
+
25
+
26
+
27
+
28
+
29
+
30
+