seungwonpark/melgan

MelGAN vocoder (compatible with NVIDIA/tacotron2)

49
/ 100
Emerging

Implements a generative adversarial vocoder that converts mel-spectrograms to raw audio with superior speed and cross-speaker generalization compared to WaveGlow. Uses PyTorch with identical mel-spectrogram preprocessing from NVIDIA/tacotron2, enabling seamless integration in text-to-speech pipelines. Includes PyTorch Hub deployment and LJSpeech-1.1 pretrained weights for immediate inference.

650 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

650

Forks

114

Language

Python

License

BSD-3-Clause

Last pushed

Oct 03, 2020

Commits (30d)

0

Get this data via API

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

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