p1an-lin-jung/WavThruVec_pytorch
An implementation of Charactr, Inc's "WavThruVec: Latent speech representation as intermediate features for neural speech synthesis"
This project helps create natural-sounding speech from text for multiple speakers. It takes raw text and pre-processed audio features (from a wav2vec 2.0 model) and converts them into spoken audio. This is ideal for speech synthesis researchers and engineers building advanced text-to-speech systems.
No commits in the last 6 months.
Use this if you need to generate high-quality, synthetic speech from written text, particularly for multi-speaker applications where custom voice control is important.
Not ideal if you're looking for a simple, out-of-the-box text-to-speech tool for everyday use without delving into model training or advanced audio processing.
Stars
29
Forks
4
Language
Python
License
—
Category
Last pushed
Sep 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/p1an-lin-jung/WavThruVec_pytorch"
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)