seanghay/KLEA

An open-source Khmer Word to Speech Model. Just single word not sentence!

36
/ 100
Emerging

Built on the VITS architecture, this model synthesizes audio waveforms from Khmer text using a conditional variational autoencoder trained on the kheng.info speech dataset of over 3000 recordings. It requires a pre-trained checkpoint (G_60000.pth) from Hugging Face and supports Python 3.9–3.11 via pip or UV, with straightforward API calls to generate WAV files from individual Khmer words.

No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 9 / 25
Community 15 / 25

How are scores calculated?

Stars

19

Forks

5

Language

Python

License

MIT

Last pushed

Dec 31, 2025

Commits (30d)

0

Get this data via API

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

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