You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Describe the bug
A clear and concise description of what the bug is.
When converting paraformer model with option '--overwrite-input-shape speech:1,83,560 speech_lengths:1 bias_embed:1,2,512', onnxsim ended with error: onnx.onnx_cpp2py_export.checker.ValidationError: Nodes in a graph must be topologically sorted, however input 'onnx::Loop_8451' of node: name: Loop_9932 OpType: Loop is not output of any previous nodes.
When I remove the option, it still happens.
Note: Before the error, onnxsim outputs 'WARNING: failed to run "SequenceEmpty" op (name is "SequenceEmpty_9930"), skip...' Model
To reproduce the problem, please post download link of your model here, or send your model to [email protected]
Here is my model, which is converted from paraformer pytorch model by modelscope. Google Drive
The text was updated successfully, but these errors were encountered:
Describe the bug
A clear and concise description of what the bug is.
When converting paraformer model with option '--overwrite-input-shape speech:1,83,560 speech_lengths:1 bias_embed:1,2,512', onnxsim ended with error:
onnx.onnx_cpp2py_export.checker.ValidationError: Nodes in a graph must be topologically sorted, however input 'onnx::Loop_8451' of node: name: Loop_9932 OpType: Loop is not output of any previous nodes.
When I remove the option, it still happens.
Note: Before the error, onnxsim outputs 'WARNING: failed to run "SequenceEmpty" op (name is "SequenceEmpty_9930"), skip...'
Model
To reproduce the problem, please post download link of your model here, or send your model to [email protected]
Here is my model, which is converted from paraformer pytorch model by modelscope.
Google Drive
The text was updated successfully, but these errors were encountered: