masoud parpanchi

thanks, the problem solved. For those who use conda, you can install Cuda 11 by this command (The current version is 11 so you don't need to specify the version...

@usimarit I have installed cudatoolkit (the version is 11 in current conda documentation ). But now I face this error >2021-03-15 08:26:03.714638: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0 2021-03-15...

@usimarit that was the full error. I couldn't solve the problem yet. May I know your concda environment config which cause to train the model?(cuda toolkit version, and other libs...

@usimarit Ok I'll share it now. But for more clarification, I write my steps : 1. create conda env `conda create -y -n tfasr python=3.8` 2. activate conda env `conda...

@usimarit thanks for the help that was the problem and removing unwanted char helped. But I have another problem now. Everything is fine But the code can not detect GPU....

> same here, any progress since then @masoudMZB not yet. If you want to use my app. use this one: https://github.com/shenasa-ai/cicada-audio-annotation-tool @dd-dos

and how much was your best CTC loss on train and validation? with and without attention

WOW :| really attention mechanism CTC loss was more? I think attention may help for better loss errors.

@light42 you said: > @Kromtar not only conversion to onnx already discussed many times since two years ago, easyocr already provide the script to export the model into onnx format....

@khawar-islam I think you should change model parameters in config.file maybe these params: network_params: hidden_size: input_channel: output_channel: hidden_size: imgH: imgW: