🌸ｌｏｔｔｅｖ．ｍｏｅ🌸vocal synth, music, art, writingdiffsinger https://lottev.moe vocal synth, music, art, writing Sat, 14 Sep 2024 20:22:15 +0000 en-US hourly 1 https://wordpress.org/?v=6.7.1 https://lottev.moe/wp-content/uploads/2021/05/cropped-icon-1-32x32.png 🌸ｌｏｔｔｅｖ．ｍｏｅ🌸vocal synth, music, art, writingdiffsinger https://lottev.moe 32 32 196733992 Project AI❤dol Public English Dataset https://lottev.moe/2024/09/project-ai%e2%9d%a4dol-public-english-dataset/ https://lottev.moe/2024/09/project-ai%e2%9d%a4dol-public-english-dataset/#respond Sat, 14 Sep 2024 20:22:15 +0000 https://lottev.moe/?p=1125 Hello everyone, I have more exciting news!

I have decided to publish a selection of my own SVS dataset for parallel training. You can use this data to help create your own DiffSinger model (or any other suitable SVS software). There has been a severe lack of easily available English female data, which motivated me to release the corpus.

I’m planning to make a proper dataset page someday, as part of the Project AI❤dol section.

I hope you enjoy! And please read the readme on the GitHub before using, thank you in advance!

Download on GitHub

~ Lotte V

]]> https://lottev.moe/2024/09/project-ai%e2%9d%a4dol-public-english-dataset/feed/ 0 1125 Hoshino Hanami ~AI❤dol~ for DiffSinger v1.0 is out! https://lottev.moe/2024/09/hoshino-hanami-ai%e2%9d%a4dol-for-diffsinger-v1-0-is-out/ https://lottev.moe/2024/09/hoshino-hanami-ai%e2%9d%a4dol-for-diffsinger-v1-0-is-out/#respond Fri, 13 Sep 2024 23:24:39 +0000 https://lottev.moe/?p=1116

Hello all!

I’m happy to announce that Hanami’s DiffSinger voicebank has finally gotten a full official release! As you can see, I ended up changing the name of the voicebank in order to match Project AI❤dol (see logo at the top of the post).

There’s some general information about the voicebank in the video description; I’m not gonna add all of that here, since that would make the post way too long. But what I will say is that she supports many different languages, has 3 different vocal modes, auto-pitch, and a custom vocoder.

I’m planning to create a dedicated DiffSinger section to the website, as well as some general information about Project AI❤dol. It’s probably gonna take a bit before I can do that though, but please be patient! It will happen, I promise.

You can download the voicebank here.

I hope you enjoy using her!

~ Lotte V

]]> https://lottev.moe/2024/09/hoshino-hanami-ai%e2%9d%a4dol-for-diffsinger-v1-0-is-out/feed/ 0 1116 Hoshino Hanami -LoveSong- for Diffsinger Beta2 is out! https://lottev.moe/2024/06/hoshino-hanami-lovesong-for-diffsinger-beta2-is-out/ https://lottev.moe/2024/06/hoshino-hanami-lovesong-for-diffsinger-beta2-is-out/#respond Wed, 26 Jun 2024 22:55:18 +0000 https://lottev.moe/?p=1095 Hey everyone,

A new beta for Hanami’s DiffSinger model is out. Hopefully LEONA will follow soon.

This beta was trained with reflow and has 3 vocal modes instead of just 1. And again, still in beta, so apologies if there are still weird quirks around! Please let me know if you encounter anything strange.

Download link on GitHub

~ Lotte V

]]> https://lottev.moe/2024/06/hoshino-hanami-lovesong-for-diffsinger-beta2-is-out/feed/ 0 1095 I’ve released Hanami and LEONA’s beta DiffSinger models https://lottev.moe/2024/04/ive-released-hanami-and-leonas-beta-diffsinger-models/ https://lottev.moe/2024/04/ive-released-hanami-and-leonas-beta-diffsinger-models/#respond Tue, 23 Apr 2024 20:31:03 +0000 https://lottev.moe/?p=1075 Hello everyone,

Yes, you’ve read that right! Hanami and LEONA’s DiffSinger models are now in beta. I won’t be adding them to their respective character pages yet due to their beta status, but I still wanted to have the links here on my site. So for now I’m posting them as a blog update.

Hanami download link

LEONA download link

I recommend you read the release notes before downloading; they contain some pretty important information.

Have fun!!!

~ Lotte V

]]> https://lottev.moe/2024/04/ive-released-hanami-and-leonas-beta-diffsinger-models/feed/ 0 1075 I hereby grant permission to use all my USTs etc. for AI pitch training https://lottev.moe/2024/03/i-hereby-grant-permission-to-use-all-my-usts-etc-for-ai-pitch-training/ https://lottev.moe/2024/03/i-hereby-grant-permission-to-use-all-my-usts-etc-for-ai-pitch-training/#respond Mon, 25 Mar 2024 21:00:36 +0000 https://lottev.moe/?p=1064 Hello everyone. The title basically already says most of it; I really don’t care if people use any of my project files for AI pitch training (Diffsinger, NNSVS, etc.). I’m not super attached to my tuning and if it helps people, hey why not.
Under ONE condition, and that is that you credit me somewhere in the readme file of your voicebank, as well as specify which file(s) you used for training. Read more over on the relevant page on this website, which has been updated accordingly.

Hopefully this helps some people with their projects, and hopefully the results will be satisfactory enough.

Speaking of Diffsinger… Be on the lookout for that the coming time.

~ Lotte V

]]> https://lottev.moe/2024/03/i-hereby-grant-permission-to-use-all-my-usts-etc-for-ai-pitch-training/feed/ 0 1064