README.md

---
title: xVASynth TTS
emoji: 🧝‍♀️🧛‍♂️🧚‍♀️
colorFrom: gray
colorTo: gray
sdk: gradio
python_version: 3.9
sdk_version: 4.20.0
models:
- Pendrokar/xvapitch_nvidia
- Pendrokar/xvapitch_expresso
- Pendrokar/TorchMoji
- Pendrokar/xvasynth_lojban
- Pendrokar/xvasynth_cabal
app_file: app.py
app_port: 7860
tags:
- tts
- t2s
- sts
- s2s
pinned: true
preload_from_hub:
- Pendrokar/xvapitch_nvidia
- Pendrokar/xvapitch_expresso
- Pendrokar/TorchMoji
- Pendrokar/xvasynth_lojban
- Pendrokar/xvasynth_cabal
license: gpl-3.0
thumbnail: https://huggingface.co/spaces/Pendrokar/xVASynth/raw/main/thumbnail.png
short_description: CPU powered, low RTF, emotional, multilingual TTS
---

DanRuta's xVASynth, GitHub repo: [https://github.com/DanRuta/xVA-Synth](https://github.com/DanRuta/xVA-Synth)

Papers:
- VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech - https://arxiv.org/abs/2106.06103
- YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for Everyone - https://arxiv.org/abs/2112.02418

Referenced papers within code:
- Multi-head attention with Relative Positional embedding - https://arxiv.org/pdf/1809.04281.pdf
- Transformer with Relative Potional Encoding- https://arxiv.org/abs/1803.02155
- SDP - https://arxiv.org/pdf/2106.06103.pdf
- Spline Flow - https://arxiv.org/abs/1906.04032

Extra:
- DeepMoji - https://arxiv.org/abs/1708.00524

xVA FastPitch:
- [1] [FastPitch: Parallel Text-to-speech with Pitch Prediction](https://arxiv.org/abs/2006.06873)
- [2] [One TTS Alignment To Rule Them All](https://arxiv.org/abs/2108.10447)

Used datasets: Unknown/Non-permissiable data