modelscope/KAN-TTS

KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-to-speech

47
/ 100
Emerging

Built on a two-stage architecture combining SAM-BERT for linguistic feature extraction and HiFi-GAN for neural vocoding, KAN-TTS enables end-to-end trainable speech synthesis across 10+ languages including Mandarin variants and European languages. The framework integrates with ModelScope for model hosting and provides complete training pipelines from data preparation through inference, supporting multilingual and multi-speaker TTS customization.

526 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

526

Forks

88

Language

Python

License

MIT

Last pushed

Dec 28, 2023

Commits (30d)

0

Get this data via API

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

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