phamkhactu
phamkhactu
Hello @Kevin-Patyk Do you need to preprocess text inputs before tokenizer??? I test by adding text input into tokenizer, and summary, but output not good, maybe need preprocess input text...
> 1. Fine-tuning should work for any language based on the Latin alphabet. If the language uses a different set of characters, you should define a new training charset configuration,...
@baudm I have try to recognize Image(contain the sentence input). I know that your model now use for word level. My question is: Does model can train input image(sentence)? 
> Tried it just now. Was able to export to ONNX using `torch.onnx.export(parseq, dummy_input, 'parseq.onnx', opset_version=14)`. Not really familiar yet with ONNX so I can't verify if the exported model...
@baudm model converted successfully to onnx, but can not load onnx model. I am asking the expert pytorch to resolve. If done I will give the final onnx
@baudm after some days, I had try to fix onnx, but can not. I very happy if you can give some line code example for infer model(torchscript), which you converted....
> Hi @phamkhactu, If possible, could you please provide the model for me to repro this issue? Thanks. @jcwchen here my model [link](https://drive.google.com/file/d/1G35Rmy7pM5lZ3E5Lrx_6S0lSEatSMT4F/view?usp=sharing) here my original model [link](https://drive.google.com/file/d/1sWIPeuhxsFt29HBi0V4HmViOzR7NeFDL/view?usp=sharing) Here my...
> because CumSum does not allow bool as an input but it gets input from previous Equal op, which only outputs bool. The exporter should handle this by something like...
> 如果是multi-news的话，要把-m设成9，但是我用3080跑了一下，也只有R1：40.4。你如果跑完了可以说一说你的结果吗？ @suwu-suwu I run the cmd in above, the difference between I and you is: m =3, my R1: 35.6630
> 可以给个邮箱相互讨论这个代码吗？ @phamkhactu @suwu-suwu yes, u can connect to me by [email protected], but you should write by English lang for i understand.