BogiHsu/Tacotron2-PyTorch

Yet another PyTorch implementation of Tacotron 2 with reduction factor and faster training speed.

47
/ 100
Emerging

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.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

148

Forks

37

Language

Python

License

MIT

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.