Voice Activity Detection
Transformers
Safetensors
PyTorch
firered-vad-stream
feature-extraction
audio
custom_code
Instructions to use MigoXV/firered-vad-stream with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MigoXV/firered-vad-stream with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MigoXV/firered-vad-stream", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "H": 256, | |
| "M": 1, | |
| "N1": 20, | |
| "N2": 0, | |
| "P": 128, | |
| "R": 8, | |
| "S1": 1, | |
| "S2": 1, | |
| "architectures": [ | |
| "FireRedVadStreamModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_firered_vad_stream.FireRedVadStreamConfig", | |
| "AutoModel": "modeling_firered_vad_stream.FireRedVadStreamModel" | |
| }, | |
| "dropout": 0.05, | |
| "dtype": "float32", | |
| "idim": 80, | |
| "ignore_index": -1, | |
| "label_pad_index": -1, | |
| "model_type": "firered-vad-stream", | |
| "odim": 1, | |
| "transformers_version": "4.57.6", | |
| "unk": "<unk>", | |
| "use_fp16": 0 | |
| } | |