can you share the script used for generating training dataset ?

[argman]

Really nice project btw!

the reason bi-lstm does not affect accuracy because lstm is more likely to model the language model(especially works for English words), but in Chinese, it depends on how you generate your data.

[senlinuc]

Yes, you are right, attention-based encoder-decoder should be better than lstm+ctc when modeling the language model. Generating Chinese dataset is more complicated than you think, but I will share my simplified code soon.

[zhousteven]

大神，很像知道你的训练数据如何将背景与字符进行合成，拉伸等操作的？能提供下脚本拜读么？

[blacklee5]

什么时候开放数据生成代码 @senlinuc

[nmwhqjl]

想测试一下效果编译都不过谁能给发个编译好的 [email protected]