Docker install for Mac M1

```
WARNING: The requested image's platform (linux/amd64) does not match the detected host platform (linux/arm64/v8) and no specific platform was requested
Start open workers
Running on local URL: http://0.0.0.0:7929

To create a public link, set `share=True` in `launch()`.
IMPORTANT: You are using gradio version 4.19.1, however version 4.44.1 is available, please upgrade.
--------
Process Process-1:
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 118, in build_model
load_ckpt(self.dur_model, f'{self.dur_exp_name}', 'dur_model')
File "/app/tts/utils/commons/ckpt_utils.py", line 87, in load_ckpt
checkpoint = torch_load_dist(ckpt_path, map_location='cpu')
File "/app/tts/utils/commons/ckpt_utils.py", line 50, in torch_load_dist
checkpoint = torch.load(tmp_path, map_location=map_location)
File "/opt/conda/lib/python3.10/site-packages/torch/serialization.py", line 1040, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/opt/conda/lib/python3.10/site-packages/torch/serialization.py", line 1262, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, 'v'.
```

Reproduce the Docker install on a Mac M1, then start with the platform warning and the traceback through /app/tts/gradio_api.py, /app/tts/infer_cli.py, and /app/tts/utils/commons/ckpt_utils.py. Determine why checkpoint loading fails and document or fix the installation so the worker starts without the reported error.

Written by the indexing model from the issue text.