Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
satyadrishti-audio-detector – AI Model by thecnical | AlphaNeural AI
You can deploy this model and start earning money today!
thecnical
/
satyadrishti-audio-detector
like
0
audio-classification
deepfake-detection
voice-clone-detection
tts-detection
forensics
satyadrishti
en
mozilla-foundation/common_voice_13_0
openslr/librispeech_asr
matthiasburger/mlaad
becoming/FakeOrReal
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
SatyaDrishti Audio Deepfake Detector
सत्यदृष्टि
— AI-Powered Digital Forensics Platform
Chandigarh Police National Hackathon 2026 — Track 4
Architecture
Backbone
: facebook/wav2vec2-base (self-supervised speech)
Sequence
: BiGRU (256 hidden x 2 layers, bidirectional)
Attention
: Multi-Head Attention (4 heads)
Head
: LayerNorm -> Dropout -> Linear(512)->GELU -> Linear(256)->GELU -> Linear(2)
Input
: 16kHz mono audio, 4 seconds
Training Datasets (~50K+ samples)
CommonVoice 13.0 — 15K real human speech
LibriSpeech — 5K real read speech
MLAAD — 10K synthetic (175 TTS models)
FakeOrReal — 8K balanced
Voice Conversion samples — 5K
Kokoro TTS — 5K generated
Performance
Val AUC
: 1.0000
Classes
: REAL (0), FAKE/SYNTHETIC (1)
Companion Model
satyadrishti-deepfake-detector
— image/video
