nnsvs

I have all my samples and labels, but every single NNSVS colab has issues. They all either crash during training or refuse to export. I have a good PC, and I have tried multiple times with multiple colabs. Help! If anybody could train him for me, that would be the nicest thing EVER. I don't...

Hello again! I'm kind of feeling out the vibes of this before I commit to it, so I'd like some community opinion. Firstly, I'm very happy with the current progress of 26's newest bank set, and I'm going to continue developing and recording it post-release in January. Despite the aggressive...

Hi! So, I've finally decided that the optimal way to train my enunu model will be local learning. As I wrote in the last txread, I have a complete 35 minutes database, only now in addition to the wav and lab files I have added the ust files needed to train the enunu model. I have downloaded the...

Hi, recently, due to the need to create my own English vooicebank, I decided to create an NNSVS model. I recorded the database for 20 minutes, marked it up in lab format (with the phonemes br, cl and pau), then uploaded it to Google drive and began training using the Diffsinger training...

The tutorial I'm using doesn't have the step of turning the lab files into usts, is there still a way to add flags during labeling?

I have a Sinsy/NNSVS-based voice in Japanese I've installed on my server, but the input MusicXML format requirement is unclear. When I try the demos (from the Sinsy site) they work fine in my api, but if I create my own MusicXML files the voice only mumbles, if it does anything at all. files...

vLabeler is an open-source voice labeling application with the following objectives: Delivering a modern and seamless UI/UX. Offering a customizable labeling process suitable for various voice generation software. Ensuring high performance and support across multiple platforms. Download...

Hi I've recently installed Enunu after this tutorial: and the Aichi one, but whenever I select Enunu as Phonemizer in Openutau and have converted the Ust to the Utaus Type (so it can sing) , there are lots of little errors, where I should be able to change how long syllables are or can shift...

How much does it usually take to label one song(for example 3 minute one)for NNSVS training?

I don't know which to use to label silence between lyrics, what's the difference?

not?? entirely sure this is the right thread, i was gonna put it in the utau thread bc yknow. i used openutau and enunu but idk anyways