LSimon95/megatts2

Unoffical implementation of Megatts2

37
/ 100
Emerging

Implements a multi-stage neural vocoder pipeline using VQ-GAN for discrete speech representation, ADM (diffusion model) for generation, and PLM for prompt-based synthesis, enabling zero-shot TTS from arbitrary-length speech prompts. Includes Montreal Forced Aligner integration for automatic phoneme-level alignment during dataset preparation. Currently supports Mandarin training with plans for multilingual support and BigVGAN vocoder replacement.

288 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 18 / 25

How are scores calculated?

Stars

288

Forks

38

Language

Python

License

MIT

Last pushed

Mar 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/LSimon95/megatts2"

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