LSimon95/megatts2

Unoffical implementation of Megatts2

44
/ 100
Emerging

This project helps researchers and developers create custom text-to-speech (TTS) systems, particularly for the Mandarin Chinese language, by processing audio and text data to build speech models. It takes raw audio (.wav) and corresponding text (.txt) files as input, then generates the necessary dataset for training advanced TTS models. This is ideal for speech scientists, linguists, or AI researchers focused on synthetic speech generation.

288 stars. No commits in the last 6 months.

Use this if you need to build and train a custom text-to-speech model, especially for Mandarin Chinese, using your own audio-text datasets.

Not ideal if you are looking for a ready-to-use text-to-speech application or a quick way to generate speech without technical setup and model training.

speech-synthesis natural-language-processing mandarin-chinese linguistics voice-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 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.