gitmylo/bark-voice-cloning-HuBERT-quantizer

The code for the bark-voicecloning model. Training and inference.

48
/ 100
Emerging

Uses HuBERT (a self-supervised speech model) with a custom quantizer to extract semantic tokens from reference voice samples, enabling high-quality voice cloning in Bark. The quantizer compresses HuBERT embeddings into discrete tokens that condition the text-to-speech model. Pretrained quantizers are available for multiple languages (English, Polish, German), and the modular design allows easy integration into existing Bark projects via simple Python APIs.

711 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

711

Forks

116

Language

Python

License

MIT

Last pushed

Sep 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/gitmylo/bark-voice-cloning-HuBERT-quantizer"

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