Skip to content
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.

Sign up for GitHub

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

Jump to bottom

add hifi-gan #4

Open
cassiotbatista opened this issue Apr 24, 2023 · 0 comments
Open

add hifi-gan #4

cassiotbatista opened this issue Apr 24, 2023 · 0 comments
Assignees
@cassiotbatista
Labels
enhancement New feature or request

Comments

@cassiotbatista
Copy link
Member

IIUC FastSpeech 2 is just the acoustic model that converts from text (or textual features including phonemes and other metadata) to spectrograms.

However to effectly synthesize speech one does actually need a vocoder to convert spectrograms to a signal in the time domain. IIRC HiFi-GAN is the one mentioned in the paper, so...
@cassiotbatista cassiotbatista added the enhancement New feature or request label Apr 24, 2023
@cassiotbatista cassiotbatista self-assigned this Apr 24, 2023
@cassiotbatista cassiotbatista mentioned this issue Apr 24, 2023
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@cassiotbatista cassiotbatista

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@cassiotbatista