text to speech checkpoints?
#1
by
singularity321
- opened
Hey there, how do I load either of these two model checkpoints:
audioldm2-speech-gigaspeech (default for TTS): Text-to-Speech, trained on GigaSpeech Dataset.
audioldm2-speech-ljspeech: Text-to-Speech, trained on LJSpeech Dataset.
To this pipeline?
Thank you!
Hey
@singularity321
- these have not yet been ported to diffusers since they came out as a follow-up to the original release. Would you mind opening a feature request on the diffusers repository so we can gauge the interest and difficulty in adding them? Thank you! https://github.com/huggingface/diffusers/issues/new?assignees=&labels=&projects=&template=feature_request.md&title=
Thanks @singularity321 !