Speech activity detection powered by ONNX Runtime for high-performance applications.
-
Supported Model:
-
Recommendation and Note:
- It is recommended to use the Audio Denoiser for optimal performance in noisy environments.
-
End-to-End Processing:
- This model includes internal
STFT
processing. - Input: Raw audio
- Output: Detected speech timestamps
- This model includes internal
-
Resources:
OS | Device | Backend | Model | Real-Time Factor (Chunk Size: 512 or 32ms) |
---|---|---|---|---|
Ubuntu-24.04 | Desktop | CPU i3-12300 |
FSMN f32 |
0.0047 |
Ubuntu-24.04 | Desktop | CPU i3-12300 |
Silero f32 |
0.0026 |
通过 ONNX Runtime 实现高性能的语音活动检测。
-
支持的模型:
-
推荐与注意:
- 建议与 音频降噪器 搭配使用,以在嘈杂环境中获得最佳性能。
-
端到端处理:
- 模型包含内部
STFT
处理。 - 输入:原始音频
- 输出:检测到的语音时间戳
- 模型包含内部
-
资源: