zsl24/Tacotron2-Mandarin-HiFiGAN
Implementation of TTS with combination of Tacotron2 and HiFi-GAN
This project helps create natural-sounding Mandarin Chinese speech from written text. You provide Mandarin text, and it generates an audio file of that text being spoken. This is useful for anyone who needs to convert written Mandarin into high-quality spoken audio, such as content creators, educators, or accessibility specialists.
No commits in the last 6 months.
Use this if you need to generate high-quality, natural-sounding Mandarin speech from text for applications like audiobooks, voiceovers, or learning materials.
Not ideal if you need to generate speech in languages other than Mandarin Chinese, or if you require real-time, low-latency speech generation for interactive applications.
Stars
11
Forks
6
Language
Python
License
MIT
Category
Last pushed
Jan 29, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/zsl24/Tacotron2-Mandarin-HiFiGAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
fatchord/WaveRNN
WaveRNN Vocoder + TTS
shangeth/wavencoder
WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation,...
rishikksh20/iSTFTNet-pytorch
iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier...
seungwonpark/melgan
MelGAN vocoder (compatible with NVIDIA/tacotron2)