[Bug] Bark does not work out of the box - invalid load key

[jooray]

Describe the bug

When I do fresh install of TTS and want to use bark model, it does not work, gives error:

(.venv) user@server : ~/tmp/tts$ tts --model_name 'tts_models/multilingual/multi-dataset/bark' --out_path test.wav --text 'We should see how this works, probably very well.'
 > tts_models/multilingual/multi-dataset/bark is already downloaded.
 > Using model: bark
/Users/user/tmp/tts/.venv/lib/python3.11/site-packages/torch/nn/utils/weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.
  warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.")
WARNING:TTS.tts.layers.bark.load_model:found outdated text model, removing...
/Users/user/Library/Application Support/tts/tts_models--multilingual--multi-dataset--bark/text_2.pt
100%|█████████████████████████████████████| 17.1k/17.1k [00:00<00:00, 20.9MiB/s]
Traceback (most recent call last):
  File "/Users/user/tmp/tts/.venv/bin/tts", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/Users/user/tmp/tts/.venv/lib/python3.11/site-packages/TTS/bin/synthesize.py", line 423, in main
    synthesizer = Synthesizer(
                  ^^^^^^^^^^^^
  File "/Users/user/tmp/tts/.venv/lib/python3.11/site-packages/TTS/utils/synthesizer.py", line 109, in __init__
    self._load_tts_from_dir(model_dir, use_cuda)
  File "/Users/user/tmp/tts/.venv/lib/python3.11/site-packages/TTS/utils/synthesizer.py", line 164, in _load_tts_from_dir
    self.tts_model.load_checkpoint(config, checkpoint_dir=model_dir, eval=True)
  File "/Users/user/tmp/tts/.venv/lib/python3.11/site-packages/TTS/tts/models/bark.py", line 281, in load_checkpoint
    self.load_bark_models()
  File "/Users/user/tmp/tts/.venv/lib/python3.11/site-packages/TTS/tts/models/bark.py", line 50, in load_bark_models
    self.semantic_model, self.config = load_model(
                                       ^^^^^^^^^^^
  File "/Users/user/tmp/tts/.venv/lib/python3.11/site-packages/TTS/tts/layers/bark/load_model.py", line 125, in load_model
    checkpoint = torch.load(ckpt_path, map_location=device)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/user/tmp/tts/.venv/lib/python3.11/site-packages/torch/serialization.py", line 1040, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/user/tmp/tts/.venv/lib/python3.11/site-packages/torch/serialization.py", line 1262, in _legacy_load
    magic_number = pickle_module.load(f, **pickle_load_args)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
_pickle.UnpicklingError: invalid load key, '<'.

To Reproduce

macOS 14.5 python version: Python 3.11.9 (main, Apr 2 2024, 08:25:04) [Clang 15.0.0 (clang-1500.3.9.4)] on darwin

python3.11 -m venv create .venv
. .venv/bin/activate
pip install TTS
tts --model_name 'tts_models/multilingual/multi-dataset/bark' --out_path test.wav --text 'We should see how this works, probably very well.'

python version: Python 3.11.9 (main, Apr 2 2024, 08:25:04) [Clang 15.0.0 (clang-1500.3.9.4)] on darwin

Expected behavior

No response

Logs

No response

Environment

{
    "CUDA": {
        "GPU": [],
        "available": false,
        "version": null
    },
    "Packages": {
        "PyTorch_debug": false,
        "PyTorch_version": "2.3.1",
        "TTS": "0.22.0",
        "numpy": "1.26.4"
    },
    "System": {
        "OS": "Darwin",
        "architecture": [
            "64bit",
            ""
        ],
        "processor": "arm",
        "python": "3.11.9",
        "version": "Darwin Kernel Version 23.5.0: Wed May  1 20:14:38 PDT 2024; root:xnu-10063.121.3~5/RELEASE_ARM64_T6020"
    }
}

### Additional context

_No response_

[eginhard]

This has been fixed in our fork, you can install it with pip install coqui-tts