Comments (8)
According to Wikipedia, it seems like you have 4 set of alphabets.
- Uyghur Arabic alphabet or UEY
- Uyghur Cyrillic alphabet or USY
- The Uyghur New Script or UYY
- Uyghur Latin alphabet or ULY
We currently have Latin model. Arabic and Cyrillic are on the way. If Uyghur use all 4 set of alphabet above, then it's not gonna be easy. You can create a pull request to add all characters and words (see #25 ), but I cannot promise to do it in the near future because my priority will have to go to popular language or set of languages that share most of characters together.
from easyocr.
According to Wikipedia, it seems like you have 4 set of alphabets.
- Uyghur Arabic alphabet or UEY
- Uyghur Cyrillic alphabet or USY
- The Uyghur New Script or UYY
- Uyghur Latin alphabet or ULY
We currently have Latin model. Arabic and Cyrillic are on the way. If Uyghur use all 4 set of alphabet above, then it's not gonna be easy. You can create a pull request to add all characters and words (see #25 ), but I cannot promise to do it in the near future because my priority will have to go to popular language or set of languages that share most of characters together.
Thanks for your reply!
Of the above four model, first model(Uyghur Arabic alphabet or UEY) is the most widely used. So just add first model(Uyghur Arabic alphabet or UEY) . I have finished the alphabet file "ug_char.txt", and now preparing the 'dict/ug.txt' common Uyghur words file.
from easyocr.
"ug_char.txt", and now preparing the 'dict/ug.tx
Hello, If it's not too much to ask, could you please share with me the "ug_char.txt", and "dict/ug.tx" files you prepared for Uygur, so that I can use them for my language?
You can download it from this EasyOCR project repository.
from easyocr.
Already explained here
from easyocr.
I'm not a language expert so you have to help me understand Uyghur language a bit. From first look, it looks like Arabic language. Let me ask a few question.
- Is Uyghur using the same script as Arabic? Or are there additional script?
- I know that in Arabic there is a specific pattern when you write character next to each other to create a word. Is Uyghur using the same pattern?
from easyocr.
I'm not a language expert so you have to help me understand Uyghur language a bit. From first look, it looks like Arabic language. Let me ask a few question.
- Is Uyghur using the same script as Arabic? Or are there additional script?
- I know that in Arabic there is a specific pattern when you write character next to each other to create a word. Is Uyghur using the same pattern?
Reply: 1.There additional script in Uyghur,Not exactly the same.
2.Yes,Uyghur using the same pattern.
from easyocr.
please make sure 'dict/ug.txt' has enough words (other languages has ~30000).
from easyocr.
"ug_char.txt", and now preparing the 'dict/ug.tx
Hello, If it's not too much to ask, could you please share with me the "ug_char.txt", and "dict/ug.tx" files you prepared for Uygur, so that I can use them for my language?
from easyocr.
Related Issues (20)
- Output of reader not shown in command window
- cv2.error: OpenCV(4.5.3) opencv/modules/core/src/alloc.cpp:73: error: (-4:Insufficient memory) Failed to allocate 113641358175 bytes in function 'OutOfMemoryError'
- RuntimeError: CUDA error: the launch timed out and was terminated HOT 1
- EasyOCR Torch Attribute problem
- The punctuation mark recognition is not accurate
- Easyocr model not extract Urdu text from images ver well why ?
- EasyOCR model not extract urdu text 100% correct ?
- How to use EasyOCR with Node.js?
- cannot import name '_accumulate' from 'torch._utils' HOT 2
- Certain broken images result in instant memory leak
- Can you run EasyOCR using only text detection without running text recognition (dbnet18) HOT 1
- Rely on a common/proven/maintained models retrieval logic
- PIL.Image.ANTIALIAS has been replaced by LANCZOS in Pillow v10.0.0, so revision is needed, thanks
- Error when reading 0 and 1 with Seven Segments Font
- while running custom easyocr,This error is occured ,How to fix these
- CRAFT model Fine Tunning via custom data no improvements and {'precision': 0, 'recall': 0.0, 'hmean': 0} on validation data
- Error on Loading "Tamil" language
- I can't solve the problem, it keeps giving me an OSError every time it's raised.
- Training Model Struggling with Character Recognition in Custom Sports Fonts HOT 5
- Not working on Windows
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from easyocr.