SolomidHero
SolomidHero
Hi, any update?
Thank you for your response! Not only `Resample` transform requires actual sample rate of input, but other layers too. Thus, expected behavior for all pipelines in my opinion requires the...
Also, according to your comment, placing `Resample` at the end of composition does a great solution, but makes overall pipeline slower, because of processing more data in steps before resample....
Close this issue with new release, pls
24kHz audio seems to be slowed down really after segmentation. Maybe somewhere writing to wav with other sample rate than used in processing? Upd: sorry, actually everything works. My problem...
Hi, I trained this model several times with different scheduling and didn't get appropriate audios by inference scripts. Can you share with some training hyperparameters if this is the case?...
@rishikksh20 ?
@J-shang Thank you I will try workaround for left `aten::zeros_like` and `aten::randint`, I guess you can find somewhere a list of all aten operations torchscript uses. aten::ScalarImplicit is used in...
Any comments? This is really simple update
@KrystalBling It might be using `print()` for tensor or its shape in your model See https://github.com/pytorch/pytorch/issues/73619