이준혁(Junhyeok Lee)
이준혁(Junhyeok Lee)
Interesting! It is still noisy after 8 iterations? We only trained and tested on 48k target so not very sure with 8k->16k setups! Reporting your results will helpful for our...
Plz run for_test.py or lightning_test.py for numerical results
I think it is similar problem that our 48k model is also not good at generating harmonics. While our 48k model generates over 12k frequency elements which is not contained...
I found that recent work from ByteDance(https://arxiv.org/pdf/2109.13731.pdf) cited our work and their results are not good too. I recommend you to read this!
Thank you for your great contribution! I add link of this issue on [README.md](https://github.com/mindslab-ai/nuwave/blob/master/README.md)!
Yes, it is also runnable with CPU (but very slow). For the music case, I don't recommend you to use this project since it is only trained with clean speech...
I think that it is different from the instrumental of the source. For example, it is hard to apply to electronic music, since high-frequency sounds of electronic do not correlate...
@dutchsing009 Hi! Sorry for the late response. To begin with, it is true that our model is not generally acting for every inputs. In addition, it need to train for...
I really appreciate your great issues! I did not notice that `i1` is *modified* Bessel function at that time. For now it seems better that replace all wrong jinc as...
Thank you for good references! Oh, he took polynomial approximation coefficients from outside. Since my first goal is understandable and flexible code with pytorch, `sinc` is not a bad option...