Docker 运行后报错

Start open workers
* Running on local URL: http://0.0.0.0:7929

To create a public link, set `share=True` in `launch()`.
Process Process-2:
Traceback (most recent call last):
File "/opt/conda/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/opt/conda/lib/python3.10/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/app/tts/gradio_api.py", line 28, in model_worker
infer_pipe = MegaTTS3DiTInfer(device=device)
File "/app/tts/infer_cli.py", line 90, in __init__
self.build_model(self.device)
File "/app/tts/infer_cli.py", line 110, in build_model
hp_dur_model = self.hp_dur_model = set_hparams(f'{self.dur_exp_name}/config.yaml', global_hparams=False)
File "/app/tts/utils/commons/hparams.py", line 134, in set_hparams
assert os.path.exists(args.config), f"{args.config} not exists"
AssertionError: ./checkpoints/duration_lm/config.yaml not exists

Read tts/infer_cli.py around build_model and tts/utils/commons/hparams.py around set_hparams, then reproduce the Docker launch and trace how ./checkpoints/duration_lm/config.yaml is expected to be provided. Done means the container starts without this assertion.

Written by the indexing model from the issue text.