在配置文件zsmeif_aispeech_config.json中设置了tensorflow--cpu 大于1时报错。

[qiaoyafeng]

` File "D:\workspace\FACEGOOD-Audio2Face\code\test\AiSpeech\zsmeif.py", line 122, in worker
output_data = get_weight(output_lpc,label_len= len(var_bs_index))
File "D:\workspace\FACEGOOD-Audio2Face\code\test\AiSpeech\lib\tensorflow\input_lpc_output_weight.py", line 62, in get_weight
output = self.run(data_temp).reshape((1,-1))
File "D:\workspace\FACEGOOD-Audio2Face\code\test\AiSpeech\lib\tensorflow\input_lpc_output_weight.py", line 49, in run
self.interpreter.invoke()
File "D:\Anaconda\envs\FACEGOOD-Audio2Face\lib\site-packages\tensorflow\lite\python\interpreter.py", line 940, in invoke
self._ensure_safe()
File "D:\Anaconda\envs\FACEGOOD-Audio2Face\lib\site-packages\tensorflow\lite\python\interpreter.py", line 556, in _ensure_safe
raise RuntimeError("""There is at least 1 reference to internal data
RuntimeError: There is at least 1 reference to internal data
in the interpreter in the form of a numpy array or slice. Be sure to
only hold the function returned from tensor() if you are using raw
data access.
0

`