FunASR 数组越界问题

Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节）

🐛 Bug

To Reproduce

Steps to reproduce the behavior (always include the command you ran):

1.情况描述模型部署在服务器上，短时间内多次调用出现以下报错，与音频质量无关，本地使用同样的环境配置和音频无法复现

报错信息 File "/root/call-center-asr/engine_frame/web/service/webrtc_asr.py", line 164, in dbfs_check result.asr_content = double_channel_wav_asr(wavfile_path, file_right_path, file_left_path, is_dbfs=True, File "/root/call-center-asr/engine_frame/web/service/webrtc_asr.py", line 178, in double_channel_wav_asr return asr_pipeline_by_file(file_left_path, file_right_path, ascii_flag, right_bfs_cal) File "/root/call-center-asr/engine_frame/web/service/webrtc_asr.py", line 241, in asr_pipeline_by_file result.left_content = inference_pipeline_1(file_left_path) File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/modelscope/pipelines/audio/funasr_pipeline.py", line 73, in __call__ output = self.model(*args, **kwargs) File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/modelscope/models/base/base_model.py", line 35, in __call__ return self.postprocess(self.forward(*args, **kwargs)) File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/modelscope/models/audio/funasr/model.py", line 61, in forward output = self.model.generate(*args, **kwargs) File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/funasr/auto/auto_model.py", line 205, in generate return self.inference_with_vad(input, input_len=input_len, **cfg) File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/funasr/auto/auto_model.py", line 270, in inference_with_vad res = self.inference(input, input_len=input_len, model=self.vad_model, kwargs=self.vad_kwargs, **cfg) File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/funasr/auto/auto_model.py", line 237, in inference results, meta_data = model.inference(**batch, **kwargs) File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/funasr/models/fsmn_vad_streaming/model.py", line 619, in inference segments_i = self.forward(**batch) File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/funasr/models/fsmn_vad_streaming/model.py", line 499, in forward self.DetectCommonFrames(cache=cache) File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/funasr/models/fsmn_vad_streaming/model.py", line 650, in DetectCommonFrames frame_state = self.GetFrameState(cache["stats"].frm_cnt - 1 - i - cache["stats"].last_drop_frames, File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/funasr/models/fsmn_vad_streaming/model.py", line 456, in GetFrameState sil_pdf_scores = [cache["stats"].scores[0][t][sil_pdf_id] for sil_pdf_id in cache["stats"].sil_pdf_ids] File "/root/miniconda3/envs/funasr/lib/python3.8/site-packages/funasr/models/fsmn_vad_streaming/model.py", line 456, in <listcomp> sil_pdf_scores = [cache["stats"].scores[0][t][sil_pdf_id] for sil_pdf_id in cache["stats"].sil_pdf_ids] IndexError: index 290 is out of bounds for dimension 0 with size 290

Code sample

`inference_pipeline_1 = pipeline( task=Tasks.auto_speech_recognition, model='iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch', model_revision="v2.0.4", vad_model='iic/speech_fsmn_vad_zh-cn-16k-common-pytorch', vad_model_revision="v2.0.4", punc_model='iic/punc_ct-transformer_zh-cn-common-vocab272727-pytorch', punc_model_revision="v2.0.4", spk_model="iic/speech_campplus_sv_zh-cn_16k-common", spk_model_revision="v2.0.2", spk_mode='punc_segment', )

content = inference_pipeline_1(audio_path) `

Expected behavior

麻烦在工程中修复这个问题，并且想知道我是否存在不当操作，导致触发了这个bug

Environment

Linux: Alibaba Cloud Linux 3.2104 LTS 64位
FunASR Version :1.0.8
ModelScope Version :1.11.1
PyTorch Version :2.1.2
pip install funasr
Python version : 3.8
GPU (NVIDIA T4)
CUDA/cuDNN version : NVIDIA-SMI 530.30.02 Driver Version: 530.30.02 CUDA Version: 12.1