Spaces:

S-Vetrivel
/

VoiceGuard-API

Sleeping

App Files Files Community

VoiceGuard-API

60.7 kB

Ctrl+K

1 contributor

History: 19 commits

S-Vetrivel

Fix SpeechBrain compatibility with newer torchaudio by mocking list_audio_backends

0b7673f 5 months ago

.agent
Initial commit: Multilingual Voice Detector with XLS-R Support 5 months ago
app
Fix SpeechBrain compatibility with newer torchaudio by mocking list_audio_backends 5 months ago
.gitignore

366 Bytes
Heavy & Accurate: Integrated SpeechBrain VAD + MMS-300M pipeline 5 months ago
Dockerfile

638 Bytes
Configure Dockerfile for Hugging Face Spaces 5 months ago
README.md

4.51 kB
Heavy & Accurate: Integrated SpeechBrain VAD + MMS-300M pipeline 5 months ago
inspect_b64.py

3.03 kB
Fix: Final audio processing fixes and enhanced logging 5 months ago
reproduce_error.py

1.22 kB
Fix: Add debug logging and robust padding to audio processing 5 months ago
requirements.txt

196 Bytes
Fix model loading error by updating torch version and improving logging 5 months ago
test.mp3

1.98 kB
Fix: Final audio processing fixes and enhanced logging 5 months ago
test_full_audio.py

3.42 kB
Implement supreme Hybrid AI detection: sliding window, spectral and temporal features, and language-aware confidence. 5 months ago
test_user_b64.py

18.9 kB
Upgrade to specialized deepfake detection model and optimize audio processing 5 months ago
verify_inference_logic.py

924 Bytes
Upgrade to specialized deepfake detection model and optimize audio processing 5 months ago
verify_model.py

682 Bytes
Heavy & Accurate: Integrated SpeechBrain VAD + MMS-300M pipeline 5 months ago
verify_nii_model.py

1.5 kB
Upgrade: Switch to MMS-300M (XLS-R) for robust multilingual deepfake detection 5 months ago
verify_speechbrain.py

1.71 kB
Heavy & Accurate: Integrated SpeechBrain VAD + MMS-300M pipeline 5 months ago