yl4579/PitchExtractor

Deep Neural Pitch Extractor for Voice Conversion and TTS Training

47
/ 100
Emerging

Uses PyWorld's hybrid `harvest`/`dio` acoustic methods to generate F0 ground truth labels during training, with automatic fallback between methods to handle extraction failures. Built as a standalone trainable module integrated into StarGANv2-VC and StyleTTS pipelines, using PyTorch with configurable batch training and Tensorboard logging.

147 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

147

Forks

34

Language

Python

License

MIT

Last pushed

Aug 22, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/yl4579/PitchExtractor"

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