yl4579/StyleTTS
Official Implementation of StyleTTS
Leverages a Transferable Monotonic Aligner (TMA) to resolve duration-alignment challenges in parallel TTS, enabling naturalistically prosodic synthesis by learning speaking styles directly from reference speech without explicit labels. Built on a two-stage training pipeline with HiFi-GAN vocoding, supporting both single-speaker (LJSpeech) and multi-speaker (LibriTTS) datasets at 24 kHz with pretrained text aligners and pitch extractors.
462 stars. No commits in the last 6 months.
Stars
462
Forks
68
Language
Python
License
MIT
Category
Last pushed
Jan 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yl4579/StyleTTS"
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