FunASR离线文件转写服务GPU版本docker部署seaco_paraformer报bug

[zihaozhu93]

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

使用docker拉取registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1官方镜像 ` sudo docker pull
registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1 mkdir -p ./funasr-runtime-resources/models sudo docker run --gpus=all -p 10098:10095 -it --privileged=true
-v $PWD/funasr-runtime-resources/models:/workspace/models
registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1

cd FunASR/runtime nohup bash run_server.sh
--download-model-dir /workspace/models
--vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx
--model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch
--punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx
--lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst
--itn-dir thuduj12/fst_itn_zh
--hotword /workspace/models/hotwords.txt > log.txt 2>&1 &

启动 damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch、damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404都能正常起来服务，启动seaco_paraformer热词模型时，指定 --model-dir iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch， 报错，

`

To Reproduce

1. Run cmd 'nohup bash run_server.sh --download-model-dir /workspace/models --model-dir iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --hotword /workspace/models/hotwords.txt > log.txt 2>&1'
2. See error Traceback (most recent call last): File "/usr/lib/python3.8/runpy.py", line 194, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/workspace/FunASR/funasr/download/runtime_sdk_download_tool.py", line 58, in main() File "/workspace/FunASR/funasr/download/runtime_sdk_download_tool.py", line 51, in main export_model.export( File "/workspace/FunASR/funasr/auto/auto_model.py", line 613, in export export_dir = export_utils.export(model=model, data_in=data_list, **kwargs) File "/workspace/FunASR/funasr/utils/export_utils.py", line 36, in export _bladedisc_opt_for_encdec(m, path=export_dir, enable_fp16=True) File "/workspace/FunASR/funasr/utils/export_utils.py", line 195, in _bladedisc_opt_for_encdec model_script = torch.jit.trace(model, input_data) File "/usr/local/lib/python3.8/dist-packages/torch/jit/_trace.py", line 750, in trace return trace_module( File "/usr/local/lib/python3.8/dist-packages/torch/jit/_trace.py", line 967, in trace_module module._c._create_method_from_trace( File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1118, in _slow_forward result = self.forward(*input, **kwargs) File "/workspace/FunASR/funasr/models/seaco_paraformer/export_meta.py", line 134, in export_backbone_forward decoder_out, decoder_hidden, _ = self.decoder( File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1107, in _slow_forward return self.forward(*input, **kwargs) RuntimeError: forward() expected at most 5 argument(s) but received 7 argument(s). Declaration: forward(torch.funasr.models.paraformer.decoder.___torch_mangle_1587. ParaformerSANMDecoderExport self, Tensor hs_pad, Tensor hlens, Tensor ys_in_pad, Tensor ys_in_lens) -> ((Tensor, Tensor))

Expected behavior

正常推理

Environment

registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-gpu-0.1.1官方镜像

Additional context