按照github的要求安装完所有东西，启动gradio没有问题，但进行声音克隆时报错：

(py311) root@u24-265k:~/autodl-tmp/code/GLM-TTS# python -m tools.gradio_app
Warning: failed to import ttsfrd, use WeTextProcessing instead

• Running on local URL: http://0.0.0.0:8048
• To create a public link, set share=True in launch().
  Loading speech tokenizer from /root/autodl-tmp/models/ZhipuAI/GLM-TTS/speech_tokenizer
  [load_quantize_encoder] start. model_path='/root/autodl-tmp/models/ZhipuAI/GLM-TTS/speech_tokenizer'
  ERROR: Inference failed: expected str, bytes or os.PathLike object, not NoneType
  Traceback (most recent call last):
  File "/root/autodl-tmp/code/GLM-TTS/tools/gradio_app.py", line 77, in run_inference
  frontend, text_frontend, _, llm, flow = get_models(use_phoneme=True, sample_rate=sample_rate)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/autodl-tmp/code/GLM-TTS/tools/gradio_app.py", line 53, in get_models
  frontend, text_frontend, speech_tokenizer, llm, flow = load_models(
  ^^^^^^^^^^^^
  File "/root/autodl-tmp/code/GLM-TTS/glmtts_inference.py", line 394, in load_models
  _model, _feature_extractor = yaml_util.load_speech_tokenizer(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/autodl-tmp/code/GLM-TTS/utils/yaml_util.py", line 64, in load_speech_tokenizer
  feature_extractor = WhisperProcessor.from_pretrained(model_path)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/envs/py311/lib/python3.11/site-packages/transformers/processing_utils.py", line 1394, in from_pretrained
  args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, **kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/envs/py311/lib/python3.11/site-packages/transformers/processing_utils.py", line 1453, in _get_arguments_from_pretrained
  args.append(attribute_class.from_pretrained(pretrained_model_name_or_path, **kwargs))
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/envs/py311/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2113, in from_pretrained
  return cls._from_pretrained(
  ^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/envs/py311/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2151, in _from_pretrained
  slow_tokenizer = (cls.slow_tokenizer_class)._from_pretrained(
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/envs/py311/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 2359, in _from_pretrained
  tokenizer = cls(*init_inputs, **init_kwargs)
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/envs/py311/lib/python3.11/site-packages/transformers/models/whisper/tokenization_whisper.py", line 291, in init
  with open(vocab_file, encoding="utf-8") as vocab_handle:
  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  TypeError: expected str, bytes or os.PathLike object, not NoneType