xuning / sherpaonnx

See also
https://github.com/k2-fsa/sherpa-onnx/issues/1695#issuecomment-2585725190

We need to place a 0 at the end of the buffer.

由于SenseVoiceSmall.from_pretrained()
    调用的funasr.auto.auto_model.AutoModel.build_model()默认device是cuda
    (在cuda available的环境中)
    ```py
    device = kwargs.get("device", "cuda")
    if not torch.cuda.is_available() or kwargs.get("ngpu", 1) == 0:
        device = "cpu"
        kwargs["batch_size"] = 1
    kwargs["device"] = device
    ```
    而export-onnx.py里的tensor默认都是cpu, 导致
    RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu
    所以直接在加载model的时候指定cpu

Co-authored-by: wangrui <wangrui@oecore.com>

…ime audio processing (#1638)

This change ensures that the main audio processing loop is not blocked by
long-running operations in `runSecondPass`, improving responsiveness and
reducing the risk of missing parts of input speech.