VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

Jungil Kong, Jihoon Park, Beomjeong Kim, Jeongmin Kim, Dohee Kong, Sangjin Kim

Unofficial implementation of the VITS2 paper, sequel to VITS paper. (thanks to the authors for their work!)

Single-stage text-to-speech models have been actively studied recently, and their results have outperformed two-stage pipeline systems. Although the previous single-stage model has made great progress, there is room for improvement in terms of its intermittent unnaturalness, computational efficiency, and strong dependence on phoneme conversion. In this work, we introduce VITS2, a single-stage text-to-speech model that efficiently synthesizes a more natural speech by improving several aspects of the previous work. We propose improved structures and training mechanisms and present that the proposed methods are effective in improving naturalness, similarity of speech characteristics in a multi-speaker model, and efficiency of training and inference. Furthermore, we demonstrate that the strong dependence on phoneme conversion in previous works can be significantly reduced with our method, which allows a fully end-toend single-stage approach.

Notes

• Supports 44100kHz.
• No Language barrier between models - Uses almost all IPA Phonemes as Input.

Prerequisites

1. Python >= 3.10
2. Tested on Pytorch version 1.13.1 with Google Colab and LambdaLabs cloud.
3. Clone this repository
4. Install python requirements. Please refer requirements.txt
   1. You may need to install espeak first: apt-get install espeak

Special mentions

• @erogol for quick feedback and guidance. (Please check his awesome CoquiTTS repo).
• @lexkoro for discussions and help with the prototype training.
• @manmay-nakhashi for discussions and help with the code.
• @athenasaurav for offering GPU support for training.
• @w11wo for ONNX support.
• @Subarasheese for Gradio UI.