Deepfake Audio Detection
D
Deepfake Audio Detection
Developed by Heem2
A deepfake audio detection model fine-tuned based on facebook/wav2vec2-base, achieving 95.45% accuracy on the evaluation set
Downloads 246
Release Time : 5/10/2024
Model Overview
This model is used to identify deepfake audio content, fine-tuned based on the wav2vec2 architecture, suitable for audio classification tasks
Model Features
High accuracy
Achieves 95.45% accuracy on the evaluation set
Based on wav2vec2 architecture
Utilizes wav2vec2's powerful audio feature extraction capabilities
Multi-ethnic English support
Training data includes multi-ethnic English pronunciations
Model Capabilities
Audio classification
Deepfake detection
Audio feature extraction
Use Cases
Security detection
Deepfake audio identification
Detects whether voice content is AI-generated deepfake audio
95.45% accuracy
Content moderation
Fake audio filtering
Automatically identifies and filters fake audio content on social media
Featured Recommended AI Models
Š 2025AIbase