maum-ai/univnet
Unofficial PyTorch Implementation of UnivNet Vocoder (https://arxiv.org/abs/2106.07889)
This project helps speech synthesis researchers and engineers create high-fidelity, natural-sounding audio from mel-spectrograms. It takes a mel-spectrogram as input and outputs a corresponding audio waveform. This is for professionals building text-to-speech systems or other applications requiring realistic synthetic speech.
282 stars. No commits in the last 6 months.
Use this if you need to convert mel-spectrograms into high-quality, natural-sounding speech waveforms efficiently.
Not ideal if you are looking for a complete text-to-speech system that handles text processing and acoustic modeling, as this only covers the vocoder component.
Stars
282
Forks
45
Language
Python
License
BSD-3-Clause
Category
Last pushed
Oct 08, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/maum-ai/univnet"
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