Hugging face phonemizerが機能せずエラーが出る。

from diffusers import DiffusionPipeline

pipe = DiffusionPipeline.from_pretrained("anhnct/audioldm2_gigaspeech")

prompt = "An female actor say with angry voice"
transcript = "wish you have a good day, i hope you never forget me"
negative_prompt = "low quality"


audio = pipe(prompt,transcript).audio[0]

Collecting espeak-phonemizer-windows
  Downloading espeak_phonemizer_windows-1.0.4-py3-none-any.whl.metadata (2.5 kB)
Downloading espeak_phonemizer_windows-1.0.4-py3-none-any.whl (9.4 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 9.4/9.4 MB 2.7 MB/s eta 0:00:00
Installing collected packages: espeak-phonemizer-windows
Successfully installed espeak-phonemizer-windows-1.0.4
vae/diffusion_pytorch_model.safetensors not found
Loading pipeline components...: 100%
 11/11 [00:03<00:00,  5.08it/s]
An error occurred while trying to fetch /root/.cache/huggingface/hub/models--anhnct--audioldm2_gigaspeech/snapshots/c812a7861f38a69441a8e0428438e782d9864614/unet: Error no file named diffusion_pytorch_model.safetensors found in directory /root/.cache/huggingface/hub/models--anhnct--audioldm2_gigaspeech/snapshots/c812a7861f38a69441a8e0428438e782d9864614/unet.
Defaulting to unsafe serialization. Pass `allow_pickle=False` to raise an error instead.
An error occurred while trying to fetch /root/.cache/huggingface/hub/models--anhnct--audioldm2_gigaspeech/snapshots/c812a7861f38a69441a8e0428438e782d9864614/projection_model: Error no file named diffusion_pytorch_model.safetensors found in directory /root/.cache/huggingface/hub/models--anhnct--audioldm2_gigaspeech/snapshots/c812a7861f38a69441a8e0428438e782d9864614/projection_model.
Defaulting to unsafe serialization. Pass `allow_pickle=False` to raise an error instead.
An error occurred while trying to fetch /root/.cache/huggingface/hub/models--anhnct--audioldm2_gigaspeech/snapshots/c812a7861f38a69441a8e0428438e782d9864614/vae: Error no file named diffusion_pytorch_model.safetensors found in directory /root/.cache/huggingface/hub/models--anhnct--audioldm2_gigaspeech/snapshots/c812a7861f38a69441a8e0428438e782d9864614/vae.
Defaulting to unsafe serialization. Pass `allow_pickle=False` to raise an error instead.
---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-22-8b84e53bddb4> in <cell line: 15>()
     13 
     14 
---> 15 audio = pipe(prompt,transcript).audio[0]

9 frames
/usr/local/lib/python3.10/dist-packages/transformers/models/vits/tokenization_vits.py in prepare_for_tokenization(self, text, is_split_into_words, normalize, **kwargs)
    188         if self.phonemize:
    189             if not is_phonemizer_available():
--> 190                 raise ImportError("Please install the `phonemizer` Python package to use this tokenizer.")
    191 
    192             filtered_text = phonemizer.phonemize(

ImportError: Please install the `phonemizer` Python package to use this tokenizer.```

!pip install datasets transformers
!pip install phonemizer
!apt-get install espeak

!pip install espeak-phonemizer-windows