BogiHsu/Tacotron2-PyTorch
Yet another PyTorch implementation of Tacotron 2 with reduction factor and faster training speed.
Implements encoder-decoder architecture with attention mechanism for mel-spectrogram prediction from text, supporting multi-GPU distributed training via PyTorch's launch utility. Outputs mel-spectrograms compatible with external vocoders like WaveGlow and Hifi-GAN for end-to-end speech synthesis. Includes preprocessing for LJ Speech dataset, TensorBoard visualization of alignments during training, and pretrained checkpoints.
148 stars. No commits in the last 6 months.
Stars
148
Forks
37
Language
Python
License
MIT
Category
Last pushed
Apr 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/BogiHsu/Tacotron2-PyTorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bshall/Tacotron
A PyTorch implementation of Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis
Kyubyong/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
Rayhane-mamah/Tacotron-2
DeepMind's Tacotron-2 Tensorflow implementation
DemisEom/SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Kyubyong/dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model