#request for hana uzaki from uzaki chan wa asobita
1 messages · Page 1 of 1 (latest)
You can check if someone already made this model. Try the following:
- Search for it in #1175430844685484042
- Alternatively, in #🔍│find-models:
- Send " @sonic hare search (name of the model)", without the ()
- Use the command
/findwith @wary path bot
- Visit https://weights.gg/ and search for the model (login required)
@fair marsh if you can prepare a decent enough clean dataset im willing to train it for ya
no i cant i need someone to make it from 0 i just want it to exist
im not good enough to make one
im sorry
you're not good enough? the fuck thats supposed to mean? that your a weak human being and dont qualify for such a task? or that your just lazy? listen all there is to it is just downloading the audio of the person off some youtube vid, seperating vocals from insrument using a website online and then just removing any extra breathing noise in an audio editor
you can do these steps both in mobile and desktop, and its easy asf, if you actually wanna do it i dont mind helping you either, anything you need. but cut all the "i cant do it" bullshit
the sad through is theres way to many characters to make voice models of, and way too many free requests, so chances of you actually getting what u want without taking any steps for it is close to zero here lol, unless ur willing to waits months or even years for it to happen on its own
oh sorry i just didnt know how to do it mb i tought it was gonna be harder and since i didnt really had much time at that moment(i had like half an hour) i tought i wouldnt be able to do it or learn how to, well im sorry and thanks for the motivation
sorry for not replying earlier i just couldnt (i didnt have wifi conection)
just to know ,do you know any apps in wich i could do it? or websites?
I got you
wow, and thank you
-doc
- How to use RVC Mainline Colab by Cauthess
- AICoverGen Colab Guide by Eddy (Spanish Helper)
- Create a model with RVC disconnected (colab) by Angetyde
If you dont have a good gpu and you’re willing to take time to set it up use kaggle
-kaggle
- Applio Notebook, by Vidal Kaggle
- Applio Notebook, by Shirou Kaggle
- Music Source Separation, by Shirou Kaggle
- UVR5 NO UI, by Eddy Kaggle
- Original W-Okada's Voice Changer, Kaggle
- Modified W-Okada's Voice Changer, Kaggle
- 🆕 UVR5 UI, by Eddy, ArisDev & Nick088 Kaggle
- 🆕 RVC AI Cover Maker UI, by Shirou & ArisDev Kaggle
- 📖 How to use RVC Mainline on Kaggle by Cauthess
Note: Kaggle limits GPU usage to 30 hours per week.
- Applio, by IA Hispano Google Colab
- RVC Disconnected, by Kit Lemonfoot Google Colab
- RVC Mainline, by Hina Google Colab
- AICoverGen-WebUI, by Hina Google Colab
- AICoverGen-NoWebUI [English], by Ardha, fixed by Eddy, Hina and Gdr Google Colab
- AICoverGen-NoWebUI [Spanish], by Eddy, Hina and Gdr Google Colab
- UVR5 NO UI, by Eddy Google Colab
- UVR5 UI, by Eddy Google Colab
- Modified W-Okada's Voice Changer, Google Colab
- FaceFusion UI, by Nick088 Google Colab
- FaceFusion NO UI, by Nick088 Google Colab
- EasyGUI, by Rejekts Google Colab
While the Colab free plan provides up to 12 hours of daily usage, the GPU is typically available for only about 4 hours each day on average.
so im gonna send one minute of dataset i could get after 1 hour (im sorry if its not enough i will do more tomorrow if i can)
i swear i will try to do more if i have the time
@fair marsh lets go to DM i can help you step by step w everything you need, since ill be training the model for you after helping you getting the dataset ready
oh nvm i see you already got some dataset ready so i guess you didnt need any help with that xD, alr then in the meantime im gonna train this model for 150 epochs ( since the dataset is small ), since theres some very high pitch vocals in the audio ( thats just how she sounds lol ) i dont think it will turn out as good but future model could prob be alot better with an improved dataset
AI HUB Docs