HuuHuy227/XphoneBert_Vits2
VITS2 extended with XPhoneBERT encoder
This project helps speech technologists and voiceover artists create high-quality, natural-sounding voiceovers and spoken content. You provide transcribed text paired with audio recordings, and it generates a text-to-speech model that can convert new text into spoken audio in a specific voice. It's designed for individuals or small teams working on single-speaker voice synthesis.
No commits in the last 6 months.
Use this if you need to train a custom text-to-speech model for a specific language and voice, especially for languages that require careful text preprocessing like Vietnamese or other non-space-separated scripts.
Not ideal if you need to train a text-to-speech model that supports multiple speakers from a single dataset.
Stars
10
Forks
3
Language
Python
License
MIT
Category
Last pushed
Oct 19, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/HuuHuy227/XphoneBert_Vits2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment