Instructions to use MidFord327/Hubert-Base-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Fairseq
How to use MidFord327/Hubert-Base-ONNX with Fairseq:
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub models, cfg, task = load_model_ensemble_and_task_from_hf_hub( "MidFord327/Hubert-Base-ONNX" ) - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -39,7 +39,7 @@ It builds upon the following models:
|
|
| 39 |
|
| 40 |
### 🟦 Inputs
|
| 41 |
- **source** | type: `float32` | shape: [batch_size, sequence_length]
|
| 42 |
-
- *Waveform PCM 32 - SR 16,000*
|
| 43 |
- **padding_mask** | type: `bool` | shape: [batch_size, sequence_length]
|
| 44 |
- It is usually a completely false array, with the same shape as the waveform. `padding_mask = np.zeros(waveform.shape, dtype=np.bool_)`
|
| 45 |
|
|
|
|
| 39 |
|
| 40 |
### 🟦 Inputs
|
| 41 |
- **source** | type: `float32` | shape: [batch_size, sequence_length]
|
| 42 |
+
- *Waveform PCM 32 - SR 16,000 - Mono*
|
| 43 |
- **padding_mask** | type: `bool` | shape: [batch_size, sequence_length]
|
| 44 |
- It is usually a completely false array, with the same shape as the waveform. `padding_mask = np.zeros(waveform.shape, dtype=np.bool_)`
|
| 45 |
|