IndexError: index 6802 is out of bounds for dimension 0 with size 6802

[lichengyang666]

What is your question?

本地运行离线asr服务，一开始正常识别，运行一段时间后报错，原来可以识别的音频现在也开始报错

Code

from funasr import AutoModel

What have you tried?

开始正常，识别了若干个离线录音之后开始报错了，还提示“Something wrong with the VAD algorithm”

What's your environment?

• OS (e.g., Linux): window（linux下面也有类似错误）
• FunASR Version (e.g., 1.0.0): 1.0.27
• ModelScope Version (e.g., 1.11.0): 1.13.3
• PyTorch Version (e.g., 2.0.0): 2.1.0
• How you installed funasr (pip, source): pip 清华源
• Python version: 3.8
• GPU (e.g., V100M32) CPU
• CUDA/cuDNN version (e.g., cuda11.7): CPU
• Docker version (e.g., funasr-runtime-sdk-cpu-0.4.1) 未使用
• Any other relevant information:

[LauraGPT]

set cache={} when decode

[di-osc]

set cache={} when decode

能否给个推理的代码示例

[LauraGPT]

set cache={} when decode

能否给个推理的代码示例

res = model.generate(
    input=input_file,
    cache={},)