Notice: In order to resolve issues more efficiently, please raise issue following the template.
（注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节）
🐛 Bug
运行demo_onnx.py报错
demo_onnx.py:
报错信息：
Traceback (most recent call last):
File "/workspace/data/wcy/code/SenseVoice/demo_onnx.py", line 13, in
model = SenseVoiceSmall(model_dir, batch_size=1, quantize=True)
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/funasr_onnx/sensevoice_bin.py", line 71, in init
model_dir = model.export(type="onnx", quantize=quantize, **kwargs)
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/funasr/auto/auto_model.py", line 664, in export
export_dir = export_utils.export(model=model, data_in=data_list, **kwargs)
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/funasr/utils/export_utils.py", line 24, in export
_onnx(
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/funasr/utils/export_utils.py", line 80, in _onnx
torch.onnx.export(
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/onnx/utils.py", line 516, in export
_export(
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/onnx/utils.py", line 1612, in _export
graph, params_dict, torch_out = _model_to_graph(
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/onnx/utils.py", line 1134, in _model_to_graph
graph, params, torch_out, module = _create_jit_graph(model, args)
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/onnx/utils.py", line 1010, in _create_jit_graph
graph, torch_out = _trace_and_get_graph_from_model(model, args)
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/onnx/utils.py", line 914, in _trace_and_get_graph_from_model
trace_graph, torch_out, inputs_states = torch.jit._get_trace_graph(
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/jit/_trace.py", line 1310, in _get_trace_graph
outs = ONNXTracedModule(
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/jit/_trace.py", line 138, in forward
graph, out = torch._C._create_graph_by_tracing(
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/jit/_trace.py", line 129, in wrapper
outs.append(self.inner(*trace_inputs))
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/root/miniforge3/envs/FunAudioLLM/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1522, in _slow_forward
result = self.forward(*input, **kwargs)
TypeError: export_forward() missing 2 required positional arguments: 'language' and 'textnorm'
To Reproduce
Steps to reproduce the behavior (always include the command you ran):
- Run cmd '....'
- See error
Code sample
Expected behavior
Environment
- OS (e.g., Linux): Linux
- FunASR Version (e.g., 1.0.0): 1.2.0
- ModelScope Version (e.g., 1.11.0): 1.21.0
- PyTorch Version (e.g., 2.0.0): 2.3.0
- How you installed funasr (
pip, source): pip install -r requirements + pip3 install -U funasr funasr-onnx
- Python version: 3.10.16
- GPU (e.g., V100M32): A100-PCIE-40GB
- CUDA/cuDNN version (e.g., cuda11.7): 12.2
- Docker version (e.g., funasr-runtime-sdk-cpu-0.4.1)
- Any other relevant information:
Additional context
我用最新的master安装测试没问题（昨天直接用官网的pip install funasr_onnx也ok）
您这边的FunASR Version (e.g., 1.0.0)
升级一下版本测试下是不是就好了？
我补充了详细的环境信息。我目前装的FunASR 1.2.0似乎已经是最新的，报错问题仍然存在
onnx 1.17.0
torch 2.4.0
funasr 1.2.1
demo_onnx.py运行正常，可以导出模型
我补充了详细的环境信息。我目前装的FunASR 1.2.0似乎已经是最新的，报错问题仍然存在
你测试的是funasr onnx，所以需要更新funasr_onnx版本。我这边最新的funasr_onnx版本是0.4.1
最新的也可以用源码安装，参考这个试一下：https://github.com/modelscope/FunASR/blob/main/runtime/python/onnxruntime/README.md （or install from source code 那里）
从源码安装最新的funasr 1.2.1后报错消失，非常感谢
FunAudioLLM
