Downloads · 30 days
0
voice-activity-detection-marblenet
Mayank022/voice-activity-detection-marblenet
voice-activity-detection-marblenet is a audio classification model from Mayank022. Use it for the audio classification task on the model card, and read the license before you ship it in a product.
Small streaming voice activity detection model trained from scratch.
Access
Public
Updated Jul 25, 2026
Repo size
4.2 MB
Likes
3
Public
Repo makeup
Click a slice to open those files.
.pt3.6 MB · 75%
At a glance
- Task
- Audio Classification
- Access
- Public
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026
- SHA
- fac0940e
Model card
From the Hugging Face model README
Mayank022/voice-activity-detection-marblenet
Small streaming voice activity detection model trained from scratch.
Files
best.pt: best PyTorch checkpoint by validation F1.last.pt: final PyTorch checkpoint.model.onnx: exported ONNX model for deployment.config.resolved.yaml: resolved training config.metrics.jsonl: training and validation metrics.product_gold_dev_eval.json: full eval output.eval_summary.json: eval metrics without per-file predictions.
Training
- Run name:
vad_marblenet_4x2x96_a100_10_20h - Best checkpoint step:
3996 - Best validation F1:
0.9876853606868101
Frame Metrics
- Precision:
1.0 - Recall:
0.9744400540628545 - F1:
0.9870545849773711 - ROC-AUC:
0.0 - PR-AUC:
0.9999958651736498 - EER:
0.0
Product Metrics
- Missed utterance rate:
0.0 - False segment rate:
0.0 - Front-end clipping p95 ms:
50.0 - Endpoint latency p95 ms:
0.0
Caveats
The default validation manifest is based on LibriSpeech dev audio and is useful for early quality checks. For production release, evaluate on hand-labeled audio from the target microphones, rooms, devices, languages, and noise conditions.
- Task
- Audio Classification
- Created
- Jul 25, 2026
- Updated
- Jul 25, 2026