加载 speaker embedding 出错

[Jackxiini]

WARNING:chattts_plus.models.llama:We detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)
text:  18%|██████████████                                                              | 71/384(max) [00:01, 43.15it/s]
INFO:ChatTTSPlusPipeline:Refine text:                                                  | 69/384(max) [00:01, 55.49it/s]
INFO:ChatTTSPlusPipeline:['正 式 而 成 立 者 ， 立 宪 之 国 家 ， 宪 法 为 人 民 所 订 定  。']
100%|████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:01<00:00,  1.70s/it]
INFO:ChatTTSPlusPipeline:loading speaker_emb from E:\Code\AudioLLM\ChatTTSPlus-copy\assets\speakers\2222.pt
WARNING:ChatTTSPlusPipeline:加载 speaker embedding 时出错: 加载的 speaker embedding 不是 tensor 类型: <class 'str'>
WARNING:ChatTTSPlusPipeline:使用空的 speaker embedding
Traceback (most recent call last):
  File "E:\Code\AudioLLM\py310env\lib\site-packages\gradio\queueing.py", line 625, in process_events
    response = await route_utils.call_process_api(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\gradio\route_utils.py", line 322, in call_process_api
    output = await app.get_blocks().process_api(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\gradio\blocks.py", line 2103, in process_api
    result = await self.call_function(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\gradio\blocks.py", line 1662, in call_function
    prediction = await utils.async_iteration(iterator)
  File "E:\Code\AudioLLM\py310env\lib\site-packages\gradio\utils.py", line 735, in async_iteration
    return await anext(iterator)
  File "E:\Code\AudioLLM\py310env\lib\site-packages\gradio\utils.py", line 729, in __anext__
    return await anyio.to_thread.run_sync(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\anyio\_backends\_asyncio.py", line 2470, in run_sync_in_worker_thread
    return await future
  File "E:\Code\AudioLLM\py310env\lib\site-packages\anyio\_backends\_asyncio.py", line 967, in run
    result = context.run(func, *args)
  File "E:\Code\AudioLLM\py310env\lib\site-packages\gradio\utils.py", line 712, in run_sync_iterator_async
    return next(iterator)
  File "E:\Code\AudioLLM\py310env\lib\site-packages\gradio\utils.py", line 873, in gen_wrapper
    response = next(iterator)
  File "E:\Code\AudioLLM\ChatTTSPlus-copy\webui.py", line 149, in generate_audio
    wav_gen = pipe.infer(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "E:\Code\AudioLLM\ChatTTSPlus-copy\chattts_plus\pipelines\chattts_plus_pipeline.py", line 543, in infer
    speaker_emb = torch.zeros((1, self.cfg.spk_emb_dim),
  File "E:\Code\AudioLLM\py310env\lib\site-packages\omegaconf\dictconfig.py", line 355, in __getattr__
    self._format_and_raise(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\omegaconf\base.py", line 231, in _format_and_raise
    format_and_raise(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\omegaconf\_utils.py", line 899, in format_and_raise
    _raise(ex, cause)
  File "E:\Code\AudioLLM\py310env\lib\site-packages\omegaconf\_utils.py", line 797, in _raise
    raise ex.with_traceback(sys.exc_info()[2])  # set env var OC_CAUSE=1 for full trace
  File "E:\Code\AudioLLM\py310env\lib\site-packages\omegaconf\dictconfig.py", line 351, in __getattr__
    return self._get_impl(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\omegaconf\dictconfig.py", line 442, in _get_impl
    node = self._get_child(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\omegaconf\basecontainer.py", line 73, in _get_child
    child = self._get_node(
  File "E:\Code\AudioLLM\py310env\lib\site-packages\omegaconf\dictconfig.py", line 480, in _get_node
    raise ConfigKeyError(f"Missing key {key!s}")
omegaconf.errors.ConfigAttributeError: Missing key spk_emb_dim
    full_key: spk_emb_dim
    object_type=dict

感谢你的训练代码！我在使用你的代码在WebUI里用你的 2222.pt （包括使用自己训练的speaker embedding）时出了以上的报错，一直没能改通，请问可以看一下吗