NATSpeech/NATSpeech

A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)

45
/ 100
Emerging

Implements parallel duration prediction and phoneme encoder architectures to eliminate sequential generation bottlenecks, leveraging Montreal Forced Aligner for automatic phoneme-level alignment during preprocessing. Built on PyTorch with a scalable modular framework supporting random-access dataset training and integrated with Hugging Face for model hosting and demos.

1,006 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,006

Forks

102

Language

Python

License

MIT

Last pushed

Apr 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/NATSpeech/NATSpeech"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.