Barbany/Multi-speaker-Neural-Vocoder
Bachelor's thesis carried at Universitat Politecnica de Catalunya in partial fullfilment of the requirements for the degree in Telecommunications Technologies and Services Engineering
This project helps researchers in speech technology by synthesizing human-like speech from existing voice recordings, generating new audio in multiple Spanish voices. It takes acoustic parameters extracted from speech and produces synthesized speech. Speech technology researchers or academics working on voice synthesis would use this.
No commits in the last 6 months.
Use this if you are a researcher developing new neural vocoders and need a multi-speaker speech synthesis baseline model for Spanish voices.
Not ideal if you need a readily deployable, production-ready speech synthesis system for general use.
Stars
16
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jul 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Barbany/Multi-speaker-Neural-Vocoder"
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)