tiberiu44/TTS-Cube
End-2-end speech synthesis with recurrent neural networks
Implements a dual-architecture pipeline with a lightweight encoder (dual-layer BiLSTM + LSTM decoder) that converts character/phoneme sequences to mel-spectrograms using guided attention for fast convergence, paired with a neural vocoder (Clarinet-based) that synthesizes audio from spectrograms. Requires no pre-aligned training data and supports both encoder-only and end-to-end synthesis modes.
223 stars. No commits in the last 6 months.
Stars
223
Forks
43
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/tiberiu44/TTS-Cube"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shangeth/wavencoder
WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation,...
fatchord/WaveRNN
WaveRNN Vocoder + TTS
kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
seungwonpark/melgan
MelGAN vocoder (compatible with NVIDIA/tacotron2)
rishikksh20/iSTFTNet-pytorch
iSTFTNet : Fast and Lightweight Mel-spectrogram Vocoder Incorporating Inverse Short-time Fourier...