一、问题现象（附报错日志上下文）：
RuntimeError: The Inner error is reported as above. The process exits for this inner error, and the current working operator name is AvgPoolV2.

0007: [PID: 157256] 2025-03-17-18:07:10.543.353 Failed to run graph fusion pass [AvgPoolV2FusionPass]. The pass type is [built-in-ai-core-graph-pass]
Solution: 1. If the pass code is custom, check the error log and the verification logic. 2. If the pass code is not custom, perform a complete or partial dump by using npucollect.sh and then send the dump to Huawei technical support for fault locating.
TraceBack (most recent call last):
op[AvgPoolV2], strides is invalid, only supports [1, 63][FUNC:Fusion][FILE:avg_pool_v2_fusion_pass.cc][LINE:793]
Failed to run graph fusion pass [AvgPoolV2FusionPass]. The pass type is [built-in-ai-core-graph-pass]
[GraphOpt][FirstRoundFusion] Fail to run graph fusion pass[AvgPoolV2FusionPass, built-in-ai-core-graph-pass]. Return value is 4294967295.[FUNC:RunOnePassFusion][FILE:graph_fusion.cc][LINE:1192]
[GraphOpt][FirstRoundFusion] MainGraph[online]: RunGraphFusion unsuccessfully.[FUNC:Fusion][FILE:graph_fusion.cc][LINE:779]
[GraphOpt][AfterFusion]Failed to do graph fusion for graph online. ErrNo is 4294967295.[FUNC:OptimizeOriginalGraph][FILE:fe_graph_optimizer.cc][LINE:359]
Call OptimizeOriginalGraph failed, ret:4294967295, engine_name:AIcoreEngine, graph_name:online[FUNC:OptimizeOriginalGraph][FILE:graph_optimize.cc][LINE:167]
build graph failed, graph id:832, ret:4294967295[FUNC:BuildModelWithGraphId][FILE:ge_generator.cc][LINE:1622]
[Build][SingleOpModel]call ge interface generator.BuildSingleOpModel failed. ge result = 4294967295[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]
[Build][Op]Fail to build op model[FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]
build op model failed, result = 500002[FUNC:ReportInnerError][FILE:log_inner.cpp][LINE:145]
(function ExecFunc)
Traceback (most recent call last):
File "/usr/local/Ascend/atb-models/funasr1/FunASR-main/tests/my_test_paraformer.py", line 9, in
res = model.generate(input=f"/root/.cache/modelscope/hub/models/iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav",
File "/usr/local/Ascend/atb-models/funasr1/FunASR-main/funasr/auto/auto_model.py", line 306, in generate
return self.inference_with_vad(input, input_len=input_len, **cfg)
File "/usr/local/Ascend/atb-models/funasr1/FunASR-main/funasr/auto/auto_model.py", line 480, in inference_with_vad
spk_res = self.inference(
File "/usr/local/Ascend/atb-models/funasr1/FunASR-main/funasr/auto/auto_model.py", line 345, in inference
res = model.inference(**batch, **kwargs)
File "/usr/local/Ascend/atb-models/funasr1/FunASR-main/funasr/models/campplus/model.py", line 141, in inference
speech = speech.to(device=kwargs["device"])
RuntimeError: The Inner error is reported as above. The process exits for this inner error, and the current working operator name is AvgPoolV2.

二、软件版本:
-- CANN 版本 (8.0.T63):
--torch2.1.0, torch_npu 2.1.0 版本:
--Python 版本 (Python 3.10):
--操作系统版本 mindie:910A-ascend_24.1.rc3-cann_8.0.t63-py_3.10-ubuntu_20.04-aarch64-mindie_1.0.T71.02

三、测试步骤：
from funasr import AutoModel

paraformer-zh is a multi-functional asr model

use vad, punc, spk or not as you need

model = AutoModel(model="paraformer-zh", vad_model="fsmn-vad", punc_model="ct-punc",
spk_model="cam++",
device="npu")
res = model.generate(input=f"{model.model_path}/example/asr_example.wav",
batch_size_s=300,
hotword='魔搭')
print(res)

四、日志信息:

日志提供方式:
将日志打包后作为附件上传。若日志大小超出附件限制，则可上传至外部网盘后提供链接。

获取方法请参考wiki：
https://gitee.com/ascend/modelzoo/wikis/如何获取日志和计算图?sort_id=4097825