Comments (5)
You'd have to collect training data similar to the data used for this project (http://www.fki.inf.unibe.ch/databases/iam-on-line-handwriting-database) and retrain the model.
That said, how well it would work will depend on some aspects of the language itself. For instance, it will work best if the language uses a small alphabet.
from handwriting-synthesis.
You'd have to collect training data similar to the data used for this project (http://www.fki.inf.unibe.ch/databases/iam-on-line-handwriting-database) and retrain the model.
That said, how well it would work will depend on some aspects of the language itself. For instance, it will work best if the language uses a small alphabet.
Inspecting the IAM dataset I recognized that it has full sentence sequences as input strokes and ascii coding. I am also interested in training the network for other languages, however the data I have consists only of words rather than whole sequences. Would it be possible to train it on single words in other languages only or does it really rely on sequences?
Also, would I have to train the network anew or could use the pretrained model for english if say the language to be trained is also from the almost same alphabet and has similarities to English?
Kind regards
from handwriting-synthesis.
Hi @sjvasquez Nice one
Can we do Handwriting Synthesis for other languages.Am interested to implement for Tamil language
Tamil. If possible kindly let us know.
have you meanwhile been able to train it for other languages?
from handwriting-synthesis.
Hello there,
I have recently created a Google Colab Notebook in which I go through all the steps to download and preprocess the data, as well as training the model and doing qualitative testing on a trained model.
If you have any suggestions or doubts, please don't bother to tell me! 😃
from handwriting-synthesis.
Hello there,
I have recently created a Google Colab Notebook in which I go through all the steps to download and preprocess the data, as well as training the model and doing qualitative testing on a trained model.
If you have any suggestions or doubts, please don't bother to tell me! 😃
I get this error when I try to run the notebook. I mean, I am just executing the notebook cells and giving correct credentials but
how do I solve this issue?
ModuleNotFoundError Traceback (most recent call last)
in ()
----> 1 from iam_dataset import IAMDataset
2 from prepare_data import main
3 from rnn import train_rnn
4
5 import numpy as np
ModuleNotFoundError: No module named 'iam_dataset'
NOTE: If your import is failing due to a missing package, you can
manually install dependencies using either !pip or !apt.
from handwriting-synthesis.
Related Issues (20)
- Is this the code underpinning https://www.calligrapher.ai ? HOT 5
- No Attribute found 'state'
- Problem with setup - versions control HOT 2
- How to train it on other language's? HOT 3
- You can use my repo that is migrated to TensorFlow v2 instead of this one HOT 4
- Can i add russian language?
- Custom Data??? HOT 2
- Style 2 - Extra Loops
- Sometimes unexpected results with this string
- Mail Merge?
- creating your own style? HOT 20
- Is there a variable that can be adjusted for legibility? HOT 1
- ModuleNotFoundError: No module named 'tensorflow.contrib' HOT 4
- Torch version or Tensorflow 2.x HOT 1
- tensor flow 1.x isn't available through pip HOT 4
- Multiple Issues within the code
- Training on own dataset
- Tutorial video as help HOT 1
- Creation of Styles HOT 2
- Quality of output SVG file HOT 5
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 handwriting-synthesis.