The labelmakr from spicytigermeat

labelmakr's Introduction

LabelMakr is a GUI tool to help users easily generate SVS phoneme-level labels. It is intended for use with DiffSinger, but is easily adaptable for other systems. Currently, LabelMakr has full support for English, Japanese, Chinese, French and Korean singing!

Please use the portable version for Windows found here.

Community Contributions 🧑‍🤝‍🧑

Le guide d'utilisation en Français peut-être trouvé ici! (Written by Mim)
한국어 사용 가이드는 여기서 찾을 수 있습니다! (Written by 군곰 KUNGOM)

Custom SOFA Model Implementation

Please check out the guide on how to implement custom SOFA models here!

Credits

Please check out credits here!

Manual Installation 🧰

Read the guide on how to manually install LabelMakr here!

labelmakr's People

Contributors

Stargazers

Watchers

labelmakr's Issues

I can't get automatic Japanese labeling in v030

I immediately installed the tool and tried to use it, but it fails here.
Will a future update allow me to use it in the same way as the previous version?

Many phonemes will stick together

inquire on svs English phnum label

Dear tigermeat,

TIGER is wonderful project,I use it in openutau.

Could I ask how you train the English svs model? I am a Graduate student,have trained chinese svs model before, and I researched training English svs model, my questions are about making english trainset,especially the phnum labeled.Do you use code in https://github.com/openvpi/MakeDiffSinger or improved the code？

I will appreciate it if you can reply .Look forward for further communication,thank you very much

Recommend Projects