[BUG]: RuntimeError: failed to load voice "ja"

[eviluess]

Describe the bug

(A clear and concise description of what the bug is.)
Installed everything, but just not running.

How To Reproduce

Steps to reproduce the behavior:

1. Config/File changes: ...
   Windows 11, following instruction. Including installing espeak and download en1, jp1, cn1,es1 and us1 to all of the following location:
   C:\Program Files\eSpeak NG\espeak-ng-data\mbrola
   C:\Program Files\eSpeak NG\espeak-ng-data\mbrola\mb
   C:\Program Files\eSpeak NG\mbrola
   C:\Program Files\eSpeak NG\mbrola\mb
2. Run command: ...
   python -m models.tts.metis.metis_infer_tse
3. See error: ...

./models/tts/maskgct/g2p\sources\g2p_chinese_model\poly_bert_model.onnx
C:\ProgramData\anaconda3\envs\maskgct\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py:121: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider'
warnings.warn(
Error: No such file or directory.
Error: No such file or directory.
Traceback (most recent call last):
File "C:\ProgramData\anaconda3\envs\maskgct\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\ProgramData\anaconda3\envs\maskgct\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "D:\AI\Metis\Amphion\models\tts\metis\metis_infer_tse.py", line 8, in
from models.tts.metis.metis import Metis
File "D:\AI\Metis\Amphion\models\tts\metis\metis.py", line 14, in
from models.tts.metis.audio_tokenizer import AudioTokenizer
File "D:\AI\Metis\Amphion\models\tts\metis\audio_tokenizer.py", line 16, in
from models.tts.maskgct.maskgct_utils import (
File "D:\AI\Metis\Amphion\models\tts\maskgct\maskgct_utils.py", line 20, in
from models.tts.maskgct.g2p.g2p_generation import g2p, chn_eng_g2p
File "D:\AI\Metis\Amphion\models\tts\maskgct\g2p\g2p_generation.py", line 10, in
from models.tts.maskgct.g2p.utils.g2p import phonemizer_g2p
File "D:\AI\Metis\Amphion\models\tts\maskgct\g2p\utils\g2p.py", line 30, in
phonemizer_ja = EspeakBackend(
File "C:\ProgramData\anaconda3\envs\maskgct\lib\site-packages\phonemizer\backend\espeak\espeak.py", line 49, in init
self._espeak.set_voice(language)
File "C:\ProgramData\anaconda3\envs\maskgct\lib\site-packages\phonemizer\backend\espeak\wrapper.py", line 249, in set_voice
raise RuntimeError( # pragma: nocover
RuntimeError: failed to load voice "ja"

Expected behavior

(A clear and concise description of what you expected to happen.)
I don't even know if this commond can actually run.

Screenshots

(If applicable, add screenshots to help explain your problem.)

Environment Information

• Operating System: Windows 11
• Python Version: Python 3.10.18
• Driver & CUDA Version: NVIDIA-SMI 576.80 Driver Version: 576.80 CUDA Version: 12.9
• Error Messages and Logs: [If applicable, provide any error messages or relevant log outputs]
  See Above

Additional context

(Add any other context about the problem here.)
run espeak-ng -v ja "こんにちは" in CLI not reporting "not loading file", I can here it reading something, but not reading this sentence.
run espeak-ng -v en "こんにちは" in CLI not reporting "not loading file", I can here it reading many "curency", not reading this sentence.
run espeak-ng -v en "hello" in CLI, I can here it reading "hello"
en1, us1, and jp1 are all in the same location.