openbmb

/

VoxCPM-0.5B

like 808

Follow

OpenBMB 4.16k

Got an Error when running on NVIDIA v100:

Traceback (most recent call last):
  File "/hpc_stor01/home/yihua.zhou/comm_scripts/tts-VoxCPM/VoxCPM-gemerate.py", line 28, in <module>
    model = VoxCPM.from_pretrained(args.model_path)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/voxcpm/core.py", line 86, in from_pretrained
    return cls(
           ^^^^
  File "/opt/conda/lib/python3.11/site-packages/voxcpm/core.py", line 36, in __init__
    self.tts_model.generate(
  File "/opt/conda/lib/python3.11/site-packages/voxcpm/model/voxcpm.py", line 176, in generate
    return next(self._generate(*args, streaming=False, **kwargs))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 36, in generator_context
    response = gen.send(None)
               ^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/voxcpm/model/voxcpm.py", line 300, in _generate
    latent_pred, pred_audio_feat = next(inference_result)
                                   ^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 36, in generator_context
    response = gen.send(None)
               ^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/voxcpm/model/voxcpm.py", line 627, in _inference
    curr_embed = self.feat_encoder_step(pred_feat.unsqueeze(1))  # b, 1, c
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 659, in _fn
    raise e.with_traceback(None) from None
torch._dynamo.exc.Unsupported: Unsupported method call
  Explanation: Dynamo does not know how to trace method `symmetric_difference` of class `type`
  Hint: Avoid calling `type.symmetric_difference` in your code.
  Hint: Please report an issue to PyTorch.

  Developer debug context: call_method BuiltinVariable(set) symmetric_difference [SetVariable(), SetVariable()] {}


from user code:
   File "/opt/conda/lib/python3.11/site-packages/einops/einops.py", line 531, in reduce
    recipe = _prepare_transformation_recipe(pattern, reduction, axes_names=tuple(axes_lengths), ndim=len(shape))
  File "/opt/conda/lib/python3.11/site-packages/torch/_dynamo/polyfills/__init__.py", line 140, in getattr_and_trace
    return fn(*args[2:], **kwargs)
  File "/opt/conda/lib/python3.11/site-packages/einops/einops.py", line 311, in _prepare_transformation_recipe
    difference = set.symmetric_difference(left.identifiers, rght.identifiers)

Set TORCHDYNAMO_VERBOSE=1 for the internal stack trace (please do this especially if you're reporting a bug to PyTorch). For even more developer context, set TORCH_LOGS="+dynamo"