Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Speaker Identification Model
|
| 2 |
+
|
| 3 |
+
This is a speaker classification model trained using MFCC features and a feedforward neural network.
|
| 4 |
+
|
| 5 |
+
## Usage
|
| 6 |
+
The model identifies which speaker is speaking among a known set. It returns predicted speaker label and confidence score.
|
| 7 |
+
|
| 8 |
+
## Files
|
| 9 |
+
- `model.pt`: Trained PyTorch model
|
| 10 |
+
- `config.json`: Model configuration
|
| 11 |
+
- `inference.py`: Example inference script
|