Cannot infer trained model

[parappanon]

Describe the bug
When I try to use svc vc for real time voice conversion, I get "RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory" after a few seconds and become unable to actually convert the voice I've trained.

The full log I get is the following:

[00:35:19] WARNING  [00:35:19] auto_predict_f0 = True in realtime inference will cause unstable voice pitch, use with caution                                                                                                      __main__.py:389
           INFO     [00:35:19] Since model_path is a directory, use logs/44k/G_3000.pth                                                                                                                                            __main__.py:405
Some weights of the model checkpoint at lengyue233/content-vec-best were not used when initializing HubertModel: ['final_proj.weight', 'final_proj.bias']
- This IS expected if you are initializing HubertModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing HubertModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
[00:35:21] WARNING  [00:35:21] /home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/so_vits_svc_fork/modules/synthesizers.py:81: UserWarning: Unused arguments: {'n_layers_q': 3, 'use_spectral_norm':      warnings.py:109
                    False}                                                                                                                                                                                                                        
                      warnings.warn(f"Unused arguments: {kwargs}")                                                                                                                                                                                
                                                                                                                                                                                                                                                  
           INFO     [00:35:21] Decoder type: hifi-gan                                                                                                                                                                          synthesizers.py:100
Traceback (most recent call last):
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/bin/svc", line 8, in <module>
    sys.exit(cli())
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/click/core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/click/core.py", line 1055, in main
    rv = self.invoke(ctx)
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/click/core.py", line 1657, in invoke
    return _process_result(sub_ctx.command.invoke(sub_ctx))
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/click/core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/click/core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/so_vits_svc_fork/__main__.py", line 407, in vc
    realtime(
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/so_vits_svc_fork/inference/main.py", line 106, in realtime
    svc_model = Svc(
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/so_vits_svc_fork/inference/core.py", line 116, in __init__
    self.load_model()
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/so_vits_svc_fork/inference/core.py", line 126, in load_model
    _ = utils.load_checkpoint(self.net_g_path, self.net_g, None)
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/so_vits_svc_fork/utils.py", line 240, in load_checkpoint
    checkpoint_dict = torch.load(f, map_location="cpu", weights_only=True)
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/torch/serialization.py", line 797, in load
    with _open_zipfile_reader(opened_file) as opened_zipfile:
  File "/home/parappa/miniconda3/envs/so-vits-svc-fork/lib/python3.10/site-packages/torch/serialization.py", line 283, in __init__
    super().__init__(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

To Reproduce
Steps to reproduce the behavior:

• Train a model for 3000 steps on https://colab.research.google.com/drive/1laRNiMSgSw_SxSnuti8oWIuC--RHzAGp
• Install so-vits-svc-fork manually through miniconda3, using Python 3.10 as the Python version on Devuan GNU/Linux
• Move the D_XXXX.pth and G_XXXX.pth files to logs/44k/ and the config.json file to configs/44k/config.json
• Activate the miniconda3 virtual enviroment for so-vits-svc-fork
• Open up a terminal and input svc vc

Additional context
Add any other context about the problem here.

[34j]

Unfortunately your checkpoint seems to be somewhat broken (this often happens when you stop training while the program is saving the ckpt), use another one.

[Penghmed]

I work offline for inference, where to put lengyue233/content-vec-best on the hard-disk?