-
Notifications
You must be signed in to change notification settings - Fork 2.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[TTS] Add period discriminator and feature matching loss to codec recipe #7884
Conversation
This PR is stale because it has been open for 14 days with no activity. Remove stale label or comment or update or this will be closed in 7 days. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Added a couple minor comments.
def __init__(self, period): | ||
super().__init__() | ||
self.period = period | ||
self.activation = nn.LeakyReLU(0.1) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add slope as an input parameter?
def output_types(self): | ||
return { | ||
"score": NeuralType(('B', 'D', 'T'), VoidType()), | ||
"fmap": [NeuralType(("B", "C", "H", "W"), VoidType())], |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nit: "B"
-> 'B'
for consistency
Other dimensions similarly
Also, are H
and W
actually T
and D
or C
?
This PR is stale because it has been open for 14 days with no activity. Remove stale label or comment or update or this will be closed in 7 days. |
This PR was closed because it has been inactive for 7 days since being marked as stale. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Signed-off-by: Ryan <rlangman@nvidia.com>
Signed-off-by: Ryan <rlangman@nvidia.com>
…ipe (#7884) * [TTS] Add period discriminator and feature matching loss to codec recipe Signed-off-by: Ryan <rlangman@nvidia.com> * [TTS] Update docs for period discriminator Signed-off-by: Ryan <rlangman@nvidia.com> --------- Signed-off-by: Ryan <rlangman@nvidia.com> Signed-off-by: stevehuang52 <heh@nvidia.com>
…ipe (NVIDIA#7884) * [TTS] Add period discriminator and feature matching loss to codec recipe Signed-off-by: Ryan <rlangman@nvidia.com> * [TTS] Update docs for period discriminator Signed-off-by: Ryan <rlangman@nvidia.com> --------- Signed-off-by: Ryan <rlangman@nvidia.com> Signed-off-by: Sasha Meister <ameister@nvidia.com>
…ipe (#7884) * [TTS] Add period discriminator and feature matching loss to codec recipe Signed-off-by: Ryan <rlangman@nvidia.com> * [TTS] Update docs for period discriminator Signed-off-by: Ryan <rlangman@nvidia.com> --------- Signed-off-by: Ryan <rlangman@nvidia.com> Signed-off-by: Pablo Garay <pagaray@nvidia.com>
…ipe (NVIDIA#7884) * [TTS] Add period discriminator and feature matching loss to codec recipe Signed-off-by: Ryan <rlangman@nvidia.com> * [TTS] Update docs for period discriminator Signed-off-by: Ryan <rlangman@nvidia.com> --------- Signed-off-by: Ryan <rlangman@nvidia.com>
What does this PR do ?
Add the feature matching loss and period discriminator used in most traditional vocoders. These will be used in my next PR which adds a configuration for creating a codec from mel spectrogram.
Collection: [TTS]
Changelog
Before your PR is "Ready for review"
Pre checks:
PR Type: