个性化语音合成训练 [ONNXRuntimeError]:7:INVALID_PROTOBUF

模型：
SambertHifigan语音合成-中文-多人预训练-16k
https://modelscope.cn/models/speech_tts/speech_sambert-hifigan_tts_zh-cn_multisp_pretrain_16k/summary

训练部分

trainer = build_trainer(
    Trainers.speech_kantts_trainer, default_args=kwargs)
trainer.train()
# 就是上面这句，在本地环境，阿里云ECS+EAIS实例上，都会报同样错误。
# 魔搭提供的Notebook GPU版本可以通过。

本地Docker环境，GPU 检查与命令 nvidia-smi，都正常
ECS+EAIS环境，查看GPU命令eais_smi，也可以通过

但这两个环境都还是会报同样错误

  File "voicegen.py", line 135, in tune
    trainer.train()
  File "/opt/conda/lib/python3.7/site-packages/modelscope/trainers/audio/tts_trainer.py", line 229, in train
    self.prepare_data()
  File "/opt/conda/lib/python3.7/site-packages/modelscope/trainers/audio/tts_trainer.py", line 208, in prepare_data
    se_model)
  File "/opt/conda/lib/python3.7/site-packages/modelscope/preprocessors/tts.py", line 37, in __call__
    speaker_name, target_lang, skip_script, se_model)
  File "/opt/conda/lib/python3.7/site-packages/modelscope/preprocessors/tts.py", line 57, in do_data_process
    targetLang, skip_script, se_model)
  File "/opt/conda/lib/python3.7/site-packages/kantts/preprocess/data_process.py", line 200, in process_data
    se_model,
  File "/opt/conda/lib/python3.7/site-packages/kantts/preprocess/se_processor/se_processor.py", line 67, in process
    sess = onnxruntime.InferenceSession(se_onnx, sess_options=opts)
  File "/opt/conda/lib/python3.7/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 360, in __init__
    self._create_inference_session(providers, provider_options, disabled_optimizers)
  File "/opt/conda/lib/python3.7/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 397, in _create_inference_session
    sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model)
onnxruntime.capi.onnxruntime_pybind11_state.InvalidProtobuf: [ONNXRuntimeError] : 7 : INVALID_PROTOBUF : Load model from /work/voiceswork/raymond/pretrain/orig_model/basemodel_16k/speaker_embedding/se.onnx failed:Protobuf parsing failed.
# python -c "import torch;torch.zeros([1]).cuda();torch.version.cuda;torch.backends.cudnn.version();torch.cuda.is_available()"