p0p4k/vits2_pytorch
unofficial vits2-TTS implementation in pytorch
Implements VITS2's architectural improvements including transformer-based normalizing flows, speaker-conditioned text encoding, and noise-scaled monotonic alignment search to reduce phoneme dependency and improve naturalness. Supports both single and multi-speaker training on LJSpeech and VCTK datasets with ONNX export capabilities, designed for seamless transfer learning from VITS checkpoints via compatible model initialization.
547 stars. No commits in the last 6 months.
Stars
547
Forks
98
Language
Python
License
MIT
Category
Last pushed
Mar 28, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/p0p4k/vits2_pytorch"
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。
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
netease-youdao/EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment