#Shadow (Fallenshadow) Speaking (RVCv2)

1 messages · Page 1 of 1 (latest)

keen shale
#

Salutations,

I am looking for an English speaking model of the VTuber fallenshadow, ideally made with RVCv2. I had tried to obtain a clip of her speaking without awkward silences, laughing, or any other weird noises (i.e. music) to help the voice model train. Attached (later) is the link to my hugging face model that I believe to be poor and "scratchy." I am not sure if my audio clip is not good, if I trained it wrong, or if it was all right but just a one-off failure.

I used ApplioV3.0.3 when trying to make her model, so it may have been switching from Mangio to Applio, but truly, I do not know. I am listing this as a Free Request as I am not in a rush to have this model, but would like to have this model be cleaner and more like the VTuber's. Included in the link is a picture, the .index, and the .pth file, as well as the audio file I used as the dataset. If there is an option to have a top-tier, high quality voice (either made and tested or an option to talk about), I may make this a Paid Request.

Thank you for your time and consideration. If you have any question, please feel free to ask :)

spring sigilBOT
#

💡 Tip: You can try using the /search or /find command from @faint scaffold or @raven moss to check if someone already made this model. Alternatively, you can check the #1175430844685484042 channel or use weights.gg, but keep in mind that weights receive the models after us, so if something new comes out, you'll find it on our server first.

keen shale