Alexandra Senderovich
Alexandra Senderovich
Thank you for your answer! The fix seems correct.
Thank you very much for your fix!
Is time stretching available in torch-audiomentations? I see only PitchShift augmentation which does not change the tempo
Is there any news? Was anyone able to reproduce ResNet + SN results?
Good question, I would also like to know the answer!
@galagam Please read ModelOpt issue I mentioned: https://github.com/NVIDIA/TensorRT-Model-Optimizer/issues/80#issuecomment-2832485911 One of the developers, @i-riyad, asked me to post the issue here.
Moreover, I would like to hear your opinion on question 1 from my original post: is there a way to finetune the model for int8 quantization in any other way,...
Hi @martinambrus, thank you very much for the logs! Could you please tell how much data you trained the model on?
It doesn't matter where you install espeak-ng. You just have to set environmental variables properly in order to use it. For Linux I set those two: ```python import os os.environ["PHONEMIZER_ESPEAK_LIBRARY"]...
@jishengpeng just to be clear: in Table 7 in the paper you report UTMOS with and without MSTFTD -- which of the four discriminators mentioned above was removed? Was it...