--- license: mit language: - en - ru - zh tags: - deepfake - cloning voce - tacotron2 - waveglow - ebsynth ---
License: MIT v1.0 GitHub

Logo

Wunjo AI: Advanced Speech & Deepfake Neural Network Tool

Documentation
Issue · Discussions · Tutorial

## About Welcome to the dedicated cloud repository for Wunjo AI's neural network models. Unlock the unparalleled capabilities of neural networks with Wunjo AI. Whether you're delving into speech synthesis, crafting deepfake animations, drawing Stable Diffusion video by text prompt or video making, Wunjo AI has got you covered. **What is stored in this repository?** - **Speech Synthesis:** [Models](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/tree/main/voice) Tacotron2 and Waveglow to speech synthesis. - **Voice Cloning:** [Models](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/tree/main/rtvc) Encoder, Vocoder and Synthesizer to cloning voice. - **Video-to-Video by Text Prompt:** Ebsynth build for CUDA 11.8 on [Linux](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/resolve/main/ebsynth/ebsynth_linux_cu118) and [Windows](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/resolve/main/ebsynth/EbSynth-Beta-Win.zip). - **Deepfake Animation:** - [Model](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/resolve/main/deepfake/faceswap.onnx) to swap faces in videos, GIFs, and photos using just a single photograph. - [Model](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/resolve/main/deepfake/emo2lip.pth) to change the emotions of a person in the video, with the help of a text description with Wav2lip architecture. - **AI Retouch Tool:** Model to [remove object](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/resolve/main/deepfake/retouch_object.pth) from video or image and model to [retouch face](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/resolve/main/deepfake/retouch_face.pth). - **Text Detection:** Model to detect text as [baseline](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/resolve/main/deepfake/vgg16_baseline.pth) and [pretrined](https://huggingface.co/wladradchenko/wunjo.wladradchenko.ru/resolve/main/deepfake/vgg16_east.pth) for weights **Applications:** From voiceovers in commercials to character voicing in games, from audiobook narrations to fun deepfake projects, Wunjo AI offers endless possibilities and all is free and local on your device. **Why Choose Wunjo AI?:** - **All-in-One:** A comprehensive tool catering to both your voice and visual AI needs. - **User-friendly:** Designed for all, from beginners to professionals. - **Privacy First:** Functions locally on your desktop, ensuring your data remains private. - **Open-source & Free:** Benefit from community-driven enhancements and enjoy the app without any cost. Step into the future of AI-powered creativity with Wunjo AI. ## Support the Project You can support the author of the project in the development of his creative ideas, or just treat him to [a cup of coffee](https://www.buymeacoffee.com/wladradchenko) in USD or [a slice of pizza](https://wladradchenko.ru/donat) in RUB. There are other ways to support the development of the project, more details on [page](https://github.com/wladradchenko/wunjo.wladradchenko.ru/wiki/Support-the-Project).
Buy a cup of coffee in USD Buy a slice of pizza in RUB
pizza coffee
## Contact Owner: [Wladislav Radchenko](https://github.com/wladradchenko/) Email: [i@wladradchenko.ru](i@wladradchenko.ru) Project on GitHub: [https://github.com/wladradchenko/wunjo.wladradchenko.ru](https://github.com/wladradchenko/wunjo.wladradchenko.ru) Web site: [wladradchenko.ru/wunjo](https://wladradchenko.ru/wunjo) ## Premise Wunjo comes from the ancient runic alphabet and represents joy and contentment, which could tie into the idea of using the application to create engaging and expressive speech. Vunyo (ᚹ) is the eighth rune of the Elder and Anglo-Saxon Futhark. Prior to the introduction of the letter W into the Latin alphabet, the letter Ƿynn (Ƿƿ) was used instead in English, derived from this rune. ## Credits * [Tacatron 2](https://github.com/NVIDIA/tacotron2) * [Waveglow](https://github.com/NVIDIA/waveglow) * [Real-Time Voice Cloning](https://github.com/CorentinJ/Real-Time-Voice-Cloning) * [Ebsynth](https://github.com/SingleZombie/ebsynth/tree/02ec8c4e4d4a568057363ae8b8f8bb8f7e4898c2)

(to top)