PlayVoice/vits_chinese
A Chinese Text-to-Speech system built on VITS with BERT embeddings for natural prosody and Microsoft Natural Speech features for reduced sound errors.
Not currently ranked — collecting fresh signals.
star history
This project implements a Text-to-Speech system based on VITS (Variational Inference for Text-to-Speech) architecture. It uses BERT to extract hidden prosody embeddings for natural grammatical pauses, incorporates inference loss techniques from Microsoft Natural Speech to reduce sound errors, and supports ONNX streaming inference for deployment.
Frequently asked
- What is PlayVoice/vits_chinese?
- A Chinese Text-to-Speech system built on VITS with BERT embeddings for natural prosody and Microsoft Natural Speech features for reduced sound errors.
- Is vits_chinese open source?
- Yes — PlayVoice/vits_chinese is open source, released under the MIT license.
- What language is vits_chinese written in?
- PlayVoice/vits_chinese is primarily written in Python.
- How popular is vits_chinese?
- PlayVoice/vits_chinese has 1.2k stars on GitHub.
- Where can I find vits_chinese?
- PlayVoice/vits_chinese is on GitHub at https://github.com/PlayVoice/vits_chinese.