部署bark-small报错：mindspore算子不支持python自带数据类型

[yanboc]

Describe the bug/ 问题描述 (Mandatory / 必填)
A clear and concise description of what the bug is.

import mindnlp
import mindspore as ms
from transformers import pipeline
import scipy

synthesiser = pipeline("text-to-speech", "<PATH_TO_MODEL>")

speech = synthesiser("Hello, my dog is cooler than you!", forward_params={"do_sample": False})

scipy.io.wavfile.write("bark_out.wav", rate=speech["sampling_rate"], data=speech["audio"])

报错信息：

Traceback (most recent call last):
  File "/code/tem/test_tts_ms/run_bark.py", line 6, in <module>
    synthesiser = pipeline("text-to-speech", "/loaded_models/suno/bark-small")
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/mindnlp/utils/decorators.py", line 15, in wrapper
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/pipelines/__init__.py", line 1008, in pipeline
    framework, model = infer_framework_load_model(
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/pipelines/base.py", line 292, in infer_framework_load_model
    model = model_class.from_pretrained(model, **kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 600, in from_pretrained
    return model_class.from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/mindnlp/utils/decorators.py", line 15, in wrapper
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/modeling_utils.py", line 317, in _wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/modeling_utils.py", line 4994, in from_pretrained
    model = cls(config, *model_args, **model_kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/models/bark/modeling_bark.py", line 1368, in __init__
    self.semantic = BarkSemanticModel(config.semantic_config)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/models/bark/modeling_bark.py", line 389, in __init__
    self.layers = nn.ModuleList([BarkBlock(config, is_causal=True, layer_idx=i) for i in range(config.num_layers)])
                                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/models/bark/modeling_bark.py", line 389, in <listcomp>
    self.layers = nn.ModuleList([BarkBlock(config, is_causal=True, layer_idx=i) for i in range(config.num_layers)])
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/models/bark/modeling_bark.py", line 290, in __init__
    self.attn = BARK_ATTENTION_CLASSES[config._attn_implementation](
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/transformers/models/bark/modeling_bark.py", line 97, in __init__
    bias = torch.tril(torch.ones((block_size, block_size), dtype=bool)).view(1, 1, block_size, block_size)
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/mindnlp/core/ops/creation.py", line 69, in ones
    output = execute('ones', size, dtype,
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/mindnlp/core/executor.py", line 5, in execute
    out, device = dispatcher.dispatch(func_name, *args, **kwargs)
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/mindnlp/core/dispatcher.py", line 62, in dispatch
    return func(*args), device
           ^^^^^^^^^^^
  File "/usr/local/lib/python3.11/site-packages/mindnlp/core/_prims/numpy.py", line 14, in ones
    return core.Tensor.from_numpy(np.ones(size, core.dtype2np[dtype]))
                                                ~~~~~~~~~~~~~^^^^^^^
KeyError: <class 'bool'>

• Hardware Environment(Ascend/GPU/CPU) / 硬件环境:

  • NPU: 300I DUO
  • CPU: Kunpeng 920 aarch64

• Software Environment / 软件环境 (Mandatory / 必填):

  • MindSpore version: 2.6.0
  • Python version: 3.11.6
  • OS platform and distribution: OpenEuler 22.03 SP4

• Excute Mode / 执行模式 (Mandatory / 必填)(PyNative/Graph):

/mode pynative

To Reproduce / 重现步骤 (Mandatory / 必填)
Steps to reproduce the behavior:

1. 运行上述代码脚本
2. See error

Expected behavior / 预期结果 (Mandatory / 必填)
A clear and concise description of what you expected to happen.

• 模型正常推理

Screenshots/ 日志 / 截图 (Mandatory / 必填)
If applicable, add screenshots to help explain your problem.

• 见问题描述

Additional context / 备注 (Optional / 选填)
Add any other context about the problem here.