search

mozilla / TTS

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
Mozilla Public License 2.0
9.41k stars 1.26k forks source link

Configurable TTS model outputs #433

Closed erogol closed 4 years ago

erogol commented 4 years ago

Right now, Tacotron model outpus linear spectrograms and Tacotron2 outputs melspectrograms. The plan is to make this configurable so that both models can compute the desired output.

repodiac commented 4 years ago

btw. I just filed an issue regarding general audio processing: https://github.com/mozilla/TTS/issues/436

erogol commented 4 years ago

is your issue related to this issue?

repodiac commented 4 years ago

somehow, it could use a GPU accelerated version, as well

erogol commented 4 years ago

this issues had nothing to do with that. I meant here the output dimensions of the models. Sorry if it is not clear.

stale[bot] commented 4 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions. You might also look our discourse page for further help. https://discourse.mozilla.org/c/tts