TypeError: must be called with a dataclass type or instance. On Audio Generation Start.

[Scopule]

Hi, this happens instantly after audio generation starts.\

Full stack:

Traceback (most recent call last):
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\gradio\queueing.py", line 625, in process_events
response = await route_utils.call_process_api(
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\gradio\route_utils.py", line 322, in call_process_api
output = await app.get_blocks().process_api(
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\gradio\blocks.py", line 2098, in process_api
result = await self.call_function(
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\gradio\blocks.py", line 1645, in call_function
prediction = await anyio.to_thread.run_sync( # type: ignore
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\anyio_backends_asyncio.py", line 2461, in run_sync_in_worker_thread
return await future
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\anyio_backends_asyncio.py", line 962, in run
result = context.run(func, *args)
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\gradio\utils.py", line 883, in wrapper
response = f(*args, **kwargs)
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows\gradio_interface.py", line 179, in generate_audio
codes = selected_model.generate(
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows\zonos\model.py", line 238, in generate
decode_one_token = torch.compile(decode_one_token, dynamic=True, disable=cg or disable_torch_compile)
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\torch_init_.py", line 2447, in compile
return torch._dynamo.optimize(
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\torch_dynamo\eval_frame.py", line 716, in optimize
return _optimize(rebuild_ctx, *args, **kwargs)
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\torch_dynamo\eval_frame.py", line 790, in optimize
compiler_config=backend.get_compiler_config()
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\torch_init.py", line 2237, in get_compiler_config
from torch._inductor.compile_fx import get_patched_config_dict
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\torch_inductor\compile_fx.py", line 49, in
from torch._inductor.debug import save_args_for_compile_fx_inner
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\torch_inductor\debug.py", line 26, in from . import config, ir # noqa: F811, this is needed
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\torch_inductor\ir.py", line 77, in
from .runtime.hints import ReductionHint
File "D:\AI Stuff\Zonos V1.0\Zonos-for-windows.venv\lib\site-packages\torch_inductor\runtime\hints.py", line 36, in
attr_desc_fields = {f.name for f in fields(AttrsDescriptor)}
File "C:\Users\Admin\AppData\Roaming\uv\python\cpython-3.10.16-windows-x86_64-none\lib\dataclasses.py", line 1198, in fields
raise TypeError('must be called with a dataclass type or instance') from None

TypeError: must be called with a dataclass type or instance

[rzgarespo]

Torch-related errors are usually due to your environment configuration, such as package conflicts, incompatible CUDA toolkit versions, path misconfiguration, or issues with the C++ compiler.
To begin with, Python 3.10 supports a version of CUDA that did not work on my PC (RTX3080), so I used Python 3.12 and CUDA 12.6.
To run hybrid models, the script will compile some packages which require your environment to support C++ compilation.
For me, WSL was the easiest way to install it, but it does have some trade-offs. WSL does not work well with VirtualBox or VMware if you plan to run virtual machines or are already running one.