[Bug] Can NOT run server with xtts_v2

[HarryBXie]

Describe the bug

1. Can NOT run server with xtts_V2.
   python TTS/server/server.py --model_name tts_models/multilingual/multi-dataset/xtts_v2 --vocoder_name vocoder_models/universal/libri-tts/wavegrad
2. Download files will miss samples directory, dvae.pth, mel_stats.pth, vs huggingface website.

To Reproduce

100% duplicate, by execute python code in command-line
python TTS/server/server.py --model_name tts_models/multilingual/multi-dataset/xtts_v2 --vocoder_name vocoder_models/universal/libri-tts/wavegrad

Expected behavior

Start server successfully. Can operate text input for TTS speaker by browser.

Logs

python TTS/server/server.py --model_name tts_models/multilingual/multi-dataset/xtts_v2 --vocoder_name vocoder_models/universal/libri-tts/wavegrad 
> tts_models/multilingual/multi-dataset/xtts_v2 is already downloaded.
 > vocoder_models/universal/libri-tts/wavegrad is already downloaded.
Traceback (most recent call last):
  File "/media/harr/King/TTS/TTS/server/server.py", line 103, in <module>
    synthesizer = Synthesizer(
  File "/media/harr/King/TTS/TTS/utils/synthesizer.py", line 93, in __init__
    self._load_tts(tts_checkpoint, tts_config_path, use_cuda)
  File "/media/harr/King/TTS/TTS/utils/synthesizer.py", line 183, in _load_tts
    self.tts_config = load_config(tts_config_path)
  File "/media/harr/King/TTS/TTS/config/__init__.py", line 82, in load_config
    ext = os.path.splitext(config_path)[1]
  File "/home/harr/anaconda3/envs/tts/lib/python3.9/posixpath.py", line 118, in splitext
    p = os.fspath(p)
TypeError: expected str, bytes or os.PathLike object, not NoneType

Environment

TTS 0.22.0 
python 3.9.21
pytorch 2.5.1
ubuntu22.04
Intel-14900HX
conda

Additional context

NOo

[HarryBXie]

@eginhard Your help is appreciated, thank you! I will check information and code.

[eginhard]

Our fork now supports all Coqui TTS models in the server. Specifying a speaker_wav file is not possible yet, this is tracked in idiap#254.

[HarryBXie]

Our fork now supports all Coqui TTS models in the server. Specifying a speaker_wav file is not possible yet, this is tracked in idiap#254.

Yes! I will try this fork, thank you!