DeepLearningExamples
DeepLearningExamples copied to clipboard
NVIDIA
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
Related to **FastPitch1.1/pytorch** **Is your feature request related to a problem? Please describe.** A question about FastPitch1.1/pytorch inferene, there are some command arguments, like `--pitch-transform-flatten`; `--pitch-transform-invert`; `--pitch-transform-amplify`. I had listened...
Is there anyway for transfer learning of the Jasper model. I have small dataset of other language, and want to transfer learn from the english checkpoint that you provided.
Related to **FastPitch1.1/pytorch** **Describe the bug** I have trained a multispeaker FastPitch, On the inference process, When I use either one of the --pitch-transform-flatten, --pitch-transform-invert, --pitch-transform-amplify to modify its predicted...
Related to **FastPitch1.1/pytorch** pytorch 1.10.2+cu111 **Is your feature request related to a problem? Please describe.** I trained FastPitch1.1 on GPU, with AMP setup before I got that `Half` is not...
Describe the bug This is not a bug, but trying to understand To Reproduce Steps to reproduce the behavior: If the training data size is larger inclduing LibriTTS clean, should...
Related to **HiFI-GAN/pytorch** **Describe the bug** export.py: No function named "load_pyt_model_for_infer" in module models.py and when I open models.py there is no function defined as load_pyt_model_infer. Because of this issue,...
Related to **Pytorch/Efficientnet QAT** **Describe the bug** why I could not get hte EfficientNetb0 QAT result as described in the webpage? **To Reproduce** Steps to reproduce the behavior: follow the...
I have pretrained Electra in the Arabic language. I got final_loss=8.84 at the end of pretraining, and everything has gone pretty well. Now, I want to use it as a...
Dear @alancucki , How to properly calculate pitch mean, std, fmin and fmax given the pitch estimated in shape of [1xmel_frames]? Yerzhan.
