---
title: README
emoji: 📚
colorFrom: red
colorTo: yellow
sdk: static
pinned: true
---

<style>
  .container {
    display: flex;
    justify-content: center;
    align-items: center;
  }
</style>

<p align="center"><img src="https://raw.githubusercontent.com/ShoukanLabs/.github/main/profile/ShoukanLab-circle.png" width="256"></p>

<p align="center", style="font-size: 2rem; font-weight: bold; color: #ff593e;">🧪 ShoukanLabs ー召喚Labsー</p>

<p align="center">Shoukan 召喚【しょうかん】 ー can be translated into either Summon or Summoning.</p>

<div class='container'>
  <a align="center" href="https://discord.gg/5bq9HqVhsJ"><img src="https://img.shields.io/badge/find_us_at_the-ShoukanLabs_Discord-invite?style=flat-square&logo=discord&logoColor=%23ffffff&labelColor=%235865F2&color=%23ffffff" width="320" alt="discord"></a>
  <!--<a align="left" style="font-size: 1.3rem; font-weight: bold; color: #5662f6;" href="https://discord.gg/5bq9HqVhsJ">find us on Discord</a>-->
</div>

## 🔎 What is ShoukanLabs?

We are a small (non-company) organisation aiming at producing cutting edge models 
- **[ButterCream](https://github.com/korakoe)**
- [AshtakaOOf](https://github.com/AshtakaOOf) 
- [Alex](https://github.com/MFAlex/) 
- [High Speed Rail Enjoyer](https://github.com/Ihateyoudattebayo) 
- [Neggles](https://github.com/neggles) 
- [ZeroCool](https://github.com/ZeroCool940711)
- [Soshyant](https://huggingface.co/Respair)
- [Wooser](https://huggingface.co/NekoMikoReimu)
- Karesto 

## 📚 Our Projects 

- **Future Projects**
  - None as of this current time

- **Current Projects**
  - A Large collection of projects surrounding TTS
    - Vokan-V2 - An iterative improvement on the Vokan TTS model, featuring several architectural improvements.
      - *More details soon...*
    - [VoPho](https://github.com/ShoukanLabs/VoPho) - A universal meta-library for phonemisation under the MIT license, with support for single language and multi-code text! These phonemisers go under an accuracy verification process, to esnure the outputs are sound.
    - VokanPipe - Our dataset curation tool designed to make dataset production simple, efficient, and largely unsupervised. 

- **Previous Projects**
  - [AniSpeech](https://huggingface.co/datasets/ShoukanLabs/AniSpeech) - An expressive dataset used to train Vokan V1 (unfortunately, not of the best quality, we're working on it!)
  - [Vokan](https://huggingface.co/ShoukanLabs/Vokan) - An expressive StyleTTS2 finetune with better 0-shot capabilities
  - [OpenNiji](https://huggingface.co/ShoukanLabs/OpenNiji) - A finetune aimed at replicating Nijijourney on Stable Diffusion.
  - [OpenNiji-V2](https://huggingface.co/ShoukanLabs/OpenNiji-V2) - A second finetune made to replicate the Nijijourney style more accurately.
 
## 💡Our Philosophy
At ShoukanLabs, we believe in:

- Contributing to the community
- Cutting-edge AI research (and teaching old models new tricks)
- Collaborative development
- Not being limited to a hobbyist level even if we're hobbyist developers