Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# HAN Speech Command Model
|
| 2 |
+
|
| 3 |
+
## Overview
|
| 4 |
+
Speech recognition model for humanoid robot voice commands.
|
| 5 |
+
Optimized for real-time command detection.
|
| 6 |
+
|
| 7 |
+
## Model Type
|
| 8 |
+
Conformer-based audio model
|
| 9 |
+
|
| 10 |
+
## Training Data
|
| 11 |
+
- Voice command dataset
|
| 12 |
+
- Synthetic speech samples
|
| 13 |
+
- Noise-augmented audio clips
|
| 14 |
+
|
| 15 |
+
## Input
|
| 16 |
+
- Audio waveform (16kHz)
|
| 17 |
+
- Mel spectrogram features
|
| 18 |
+
|
| 19 |
+
## Output
|
| 20 |
+
- Command classification
|
| 21 |
+
- Intent prediction
|
| 22 |
+
|
| 23 |
+
## Framework
|
| 24 |
+
PyTorch + Torchaudio
|
| 25 |
+
|
| 26 |
+
## Use Case
|
| 27 |
+
- Voice control
|
| 28 |
+
- Smart assistant integration
|
| 29 |
+
- Human-robot interaction
|
| 30 |
+
|
| 31 |
+
## License
|
| 32 |
+
MIT
|