Warmup multiple values for keyword argument chunk_duration

[MarcBomber]

Hi, I want to try the realtime MOSS. The warmup throws an error. Any Idea what is happening?

(venv) C:\dev\OpenMOSS\MOSS-TTS\moss_tts_realtime>python3 app.py

• Running on local URL: http://0.0.0.0:18082
  config.json: 2.39kB [00:00, 2.29MB/s]
  c:\dev\OpenMOSS\MOSS-TTS\venv\lib\site-packages\huggingface_hub\file_download.py:129: UserWarning: huggingface_hub cache-system uses symlinks by default to efficiently store duplicated files but your machine does not support them in C:\Users\MarcBomber.cache\huggingface\hub\models--OpenMOSS-Team--MOSS-TTS-Realtime. Caching files will still work but in a degraded version that might require more space on your disk. This warning can be disabled by setting the HF_HUB_DISABLE_SYMLINKS_WARNING environment variable. For more details, see https://huggingface.co/docs/huggingface_hub/how-to-cache#limitations.
  To support symlinks on Windows, you either need to activate Developer Mode or to run Python as an administrator. In order to activate developer mode, see this article: https://docs.microsoft.com/en-us/windows/apps/get-started/enable-your-device-for-development
  warnings.warn(message)
  You are using a model of type moss_tts_realtime to instantiate a model of type . This is not supported for all configurations of models and can yield errors.
  tokenizer_config.json: 5.44kB [00:00, 10.9MB/s]
  Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
  tokenizer.json: 100%|█████████████████████████████████████████████████████████████| 11.4M/11.4M [00:01<00:00, 9.43MB/s]
• To create a public link, set share=True in launch().
  model.safetensors: 100%|███████████████████████████████████████████████████████████| 4.66G/4.66G [00:36<00:00, 127MB/s]
  Loading weights: 100%|████| 403/403 [00:00<00:00, 3374.35it/s, Materializing param=local_transformer.model.norm.weight]
  Loading weights: 100%|█| 1600/1600 [00:00<00:00, 2539.55it/s, Materializing param=quantizer.quantizers.31.out_proj.para
  c:\dev\OpenMOSS\MOSS-TTS\venv\lib\site-packages\torch_inductor\compile_fx.py:321: UserWarning: TensorFloat32 tensor cores for float32 matrix multiplication available but not enabled. Consider setting torch.set_float32_matmul_precision('high') for better performance.
  warnings.warn(
  [MossTTSRealtime][warmup-error] transformers_modules.OpenMOSS_hyphen_Team.MOSS_hyphen_Audio_hyphen_Tokenizer.8846e01bba2030c66b6cdbaabf14e70e77aec3b7.modeling_moss_audio_tokenizer.MossAudioTokenizerModel.decode() got multiple values for keyword argument 'chunk_duration'

[Zhyw0]

We fix it in #95, you can follow this change and rerun app.py.