DemisEom/SpecAugment

A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain

51
/ 100
Established

Applies time warping and frequency/time masking directly to mel-spectrograms for robust speech augmentation across both TensorFlow and PyTorch backends. The implementation accepts pre-computed spectrograms via librosa and modifies them through temporal warping, consecutive frequency channel masking, and utterance-level time masking. Includes test utilities with LibriSpeech dataset examples for validation.

656 stars. No commits in the last 6 months.

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

How are scores calculated?

Stars

656

Forks

135

Language

Python

License

Apache-2.0

Last pushed

Apr 05, 2022

Commits (30d)

0

Get this data via API

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

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