nakamura

@liziru Hi, How can you get val_loss around -21? In my case I get train_loss 0.0011 val_loss:46 I didn't change a thing in this repository, or data configuration 500h (same...

@nestyme does recording audio in 48000hz work in this model?

@StuartIanNaylor Hi, I have some issues on training this nice model. I followed step by step reading through documentation. training data created by breizhn/DNS-challenge repository I get validation loss around...

@StuartIanNaylor Thanks for fast reply, I've tried both 40h and 500h ( both created automatically by python script provided (noisyspeech_synthesizer_multiprocessing.py) validation test data was also splitted by script ( split_dns_corpus.py)....

@StuartIanNaylor I am still struggling with val loss in training DTLN I've checked data set randomly and had no problem. Can I figure out which one of 1st dataset is...

@linnnff @hsl20130659 Hi, How did you convert stn model to onnx? I am so much struggling with stn. stn has pytorch function which is not supported converting opset

Thank you for sharing this wonderful project However, I also have download problem, Can i get another download link? thanks in advance, [email protected]

how did you fix this issue? maybe , is it overfitting?

@sirius-ai Thanks for such a great work! what does T_length mean? i am confused with args.lpr_max_len if I change lpr_max_len then output shape could change? for now my output shape...

@ralienpp did you solve it ? I have the same issue