| library_name: transformers | |
| tags: | |
| - audio | |
| - voice-activity-detection | |
| - pytorch | |
| - safetensors | |
| base_model: | |
| - FireRedTeam/FireRedVAD | |
| # FireRed VAD Stream | |
| 这是由原始 `FireRedTeam/FireRedVAD/Stream-VAD` 转换得到的标准 Hugging Face 模型仓库。 | |
| 仓库内容： | |
| - `model.safetensors`：流式 VAD 模型权重 | |
| - `config.json`：`firered-vad-stream` 模型配置和 AutoClass 映射 | |
| - `cmvn.ark`：与原始模型一致的 CMVN 统计量 | |
| - `configuration_firered_vad_stream.py` / `modeling_firered_vad_stream.py` / `module_firered_vad_stream.py`：HF remote code | |
| 加载示例： | |
| ```python | |
| from transformers import AutoModel | |
| model = AutoModel.from_pretrained( | |
| "MigoXV/firered-vad-stream", | |
| trust_remote_code=True, | |
| ) | |
| ``` | |