CosyVoice2模型推理准备；ATC转换脚本执行报错

一、问题现象（附报错日志上下文）：
修改好onnx模型之后，运行atc模型转换命令报错。

二、软件版本:
-- CANN 版本 (e.g., CANN 3.0.x，5.x.x):8.2.RC1
--Tensorflow/Pytorch/MindSpore 版本:没安装
--Python 版本 (e.g., Python 3.7.5):3.10.14
-- MindStudio版本 (e.g., MindStudio 2.0.0 (beta3)):没安装
--操作系统版本 (e.g., Ubuntu 18.04):ubuntu 20.04

三、测试步骤：
按照文档https://gitee.com/ascend/ModelZoo-PyTorch/tree/master/ACL_PyTorch/built-in/audio/CosyVoice执行。
进行到模型推理部分，修改完onnx模型，开始执行onnx到OM模型转换步骤的atc命令。
模型修改部分已执行成功，生成了对应的文件。然后执行命令：atc --framework=5 --soc_version=Ascend910B4 --model ./CosyVoice2-0.5B/speech_token_md.onnx --output ./CosyVoice2-0.5B/speech --input_shape="feats:1,128,-1;feats_length:1" --precision_mode allow_fp32_to_fp16
报错如下：
ATC start working now, please wait for a moment.
...
ATC run failed, Please check the detail log, Try 'atc --help' for more information
E40001: [PID: 189976] 2025-09-02-11:01:01.881.116 Value [/home/kuntai/asrTest/cmake-4.1/bin:/usr/local/Ascend/ascend-toolkit/latest/bin:/usr/local/Ascend/ascend-toolkit/latest/compiler/ccec_compiler/bin:/usr/local/Ascend/ascend-toolkit/latest/tools/ccec_compiler/bin:/home/kuntai/.local/bin:/home/kuntai/asrTest/cmake-4.1/bin:/usr/local/Ascend/ascend-toolkit/latest/bin:/usr/local/Ascend/ascend-toolkit/latest/compiler/ccec_compiler/bin:/usr/local/Ascend/ascend-toolkit/latest/tools/ccec_compiler/bin:/usr/local/freeswitch/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin] for environment variable [PATH] is invalid when executing the cmd python3-config --prefix.
        Possible Cause: The current value of environment variable is not effective.
        Solution: Reset the environment variable by referring to the installation guide.
        TraceBack (most recent call last):
        Fail to initialize handle manager.[FUNC:Initialize][FILE:python_adapter_manager.cc][LINE:40]
        Failed to initialize TeConfigInfo.
        [GraphOpt][InitializeInner][InitTbeFunc] Failed to init tbe.[FUNC:InitializeTeFusion][FILE:tbe_op_store_adapter.cc][LINE:1921]
        [GraphOpt][InitializeInner][InitTeFusion]: Failed to initialize TeFusion.[FUNC:InitializeInner][FILE:tbe_op_store_adapter.cc][LINE:1888]
        [SubGraphOpt][PreCompileOp][InitAdapter] InitializeAdapter adapter [tbe_op_adapter] failed! Ret [4294967295][FUNC:InitializeAdapter][FILE:op_store_adapter_manager.cc][LINE:79]
        [SubGraphOpt][PreCompileOp][Init] Initialize op store adapter failed, OpsStoreName[tbe-custom].[FUNC:Initialize][FILE:op_store_adapter_manager.cc][LINE:120]
        [FusionMngr][Init] Op store adapter manager init failed.[FUNC:Initialize][FILE:fusion_manager.cc][LINE:115]
        PluginManager InvokeAll failed.[FUNC:Initialize][FILE:ops_kernel_manager.cc][LINE:83]
        OpsManager initialize failed.[FUNC:InnerInitialize][FILE:gelib.cc][LINE:239]
        GELib::InnerInitialize failed.[FUNC:Initialize][FILE:gelib.cc][LINE:164]
提示似乎环境变量有问题。但是求助了大模型，反复修改折腾没有解决。而且当前环境执行torch-npu示例以及其它使用npu的代码正常。此前CANN8.1.RC1有问题，升级到8.2.RC1之后还是一样的现象。请帮忙看一下能不能找到原因，让atc能正常运行。

Ascend/ModelZoo-PyTorch

内容风险标识

评论 (1)

Ascend/ModelZoo-PyTorch .gitee-modal { width: 500px !important; }

内容风险标识