when I use mindnlp "model = Wav2Vec2ForCTCnCLS.from_pretrained('/media/data1/xidian/kdl/mindspore_nlp/facebook/wav2vec2-base-960h')"
the warning "The following parameters in models are missing parameter: ['wav2vec2.masked_spec_embed', 'cls_head.weight', 'cls_head.bias']" appears, when I forward pass the model on CPU with "x = ops.randn((64, 32000)), print(model(x))" it can work well, while I forward pass the model on Ascend it appears the following error:
Traceback (most recent call last):
File "model.py", line 119, in
print(model(x))
File "/home/xidian/.conda/envs/msdelkon/lib/python3.8/site-packages/mindspore/nn/cell.py", line 705, in call
raise err
File "/home/xidian/.conda/envs/msdelkon/lib/python3.8/site-packages/mindspore/nn/cell.py", line 702, in call
_pynative_executor.end_graph(self, output, *args, **kwargs)
File "/home/xidian/.conda/envs/msdelkon/lib/python3.8/site-packages/mindspore/common/api.py", line 1215, in end_graph
self._executor.end_graph(obj, output, *args, *(kwargs.values()))
RuntimeError: aclrtMemcpyAsync depend tensor failed! tensor size is 0 and address size is 0

• Ascend Error Message:

EE1001: The argument is invalid.Reason: Check param failed, cnt can not be 0.
Solution: 1.Check the input parameter range of the function. 2.Check the function invocation relationship.
TraceBack (most recent call last):
The argument is invalid.Reason: rtMemcpyAsync execute failed, reason=[invalid value]
asynchronized memcpy failed, kind = 2, runtime result = 107000[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161]

(Please search "Ascend Error Message" at https://www.mindspore.cn for error code description)

• Ascend Warning Message:

W49999: If want to reuse binary file, please donwload binary file and install first![FUNC:BuildFusionOp][FILE:fusion_manager.cc][LINE:3763]

• C++ Call Stack: (For framework developers)

mindspore/ccsrc/plugin/device/ascend/kernel/acl/acl_kernel_mod.cc:52 GetDependValueTensor

That's why? Is there any solution?