kshitijbhandari/Speech-Detection----Spoken-Digit
Spoken digit recognition (0–9) using LSTM networks. Compares raw waveforms vs. log-mel spectrograms with and without data augmentation. Best model achieves 95.5% F1 using augmented spectrograms. Built with TensorFlow, Librosa, and the Free Spoken Digit Dataset.
11
/ 100
Experimental
No License
No Package
No Dependents
Maintenance
10 / 25
Adoption
0 / 25
Maturity
1 / 25
Community
0 / 25
Stars
—
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/kshitijbhandari/Speech-Detection----Spoken-Digit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.