dessa-oss/fake-voice-detection

Using temporal convolution to detect Audio Deepfakes

49
/ 100
Emerging

# Technical Summary Builds on ASVSpoof 2019 logical-access dataset with spectrogram preprocessing and includes a pre-trained baseline model (85% accuracy) for immediate inference on custom audio files. Leverages Foundations Atlas for experiment tracking, hyperparameter search automation, and TensorBoard integration to streamline model training and evaluation workflows. Supports distributed job submission and artifact management across GPU-accelerated systems (32GB+ RAM, ≥1 GPU).

383 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

383

Forks

86

Language

Python

License

Apache-2.0

Last pushed

Nov 21, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/dessa-oss/fake-voice-detection"

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