zipformer onnx转rknn失败

[autumnqin]

用sample里提供中英文zipformer模型，onnx转rknn可以成功。换了一个日语版本的zipformer模型就失败了，url是：
https://github.com/k2-fsa/sherpa-onnx/releases/download/asr-models/sherpa-onnx-zipformer-ja-reazonspeech-2024-08-01.tar.bz2

错误提示：
I rknn-toolkit2 version: 2.3.0
--> Config model
done
--> Loading model
I Loading : 100%|███████████████████████████████████████████████| 846/846 [00:00<00:00, 9154.16it/s]
E load_onnx: The input shape ['N', 'T', 80] of 'x' is not support!
Please set the 'inputs' / 'input_size_list' parameters of 'rknn.load_onnx', or set the 'dyanmic_input' parameter of 'rknn.config' to fix the input shape!
I ===================== WARN(0) =====================
E rknn-toolkit2 version: 2.3.0
E load_onnx: Traceback (most recent call last):
File "rknn/api/rknn_log.py", line 344, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper
File "rknn/api/rknn_base.py", line 1534, in rknn.api.rknn_base.RKNNBase.load_onnx
File "rknn/api/rknn_base.py", line 702, in rknn.api.rknn_base.RKNNBase._create_ir_and_inputs_meta
File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e
ValueError: The input shape ['N', 'T', 80] of 'x' is not support!
Please set the 'inputs' / 'input_size_list' parameters of 'rknn.load_onnx', or set the 'dyanmic_input' parameter of 'rknn.config' to fix the input shape!

I ===================== WARN(0) =====================
E rknn-toolkit2 version: 2.3.0
Traceback (most recent call last):
File "rknn/api/rknn_log.py", line 344, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper
File "rknn/api/rknn_base.py", line 1534, in rknn.api.rknn_base.RKNNBase.load_onnx
File "rknn/api/rknn_base.py", line 702, in rknn.api.rknn_base.RKNNBase._create_ir_and_inputs_meta
File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e
ValueError: The input shape ['N', 'T', 80] of 'x' is not support!
Please set the 'inputs' / 'input_size_list' parameters of 'rknn.load_onnx', or set the 'dyanmic_input' parameter of 'rknn.config' to fix the input shape!

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "convert.py", line 47, in
ret = rknn.load_onnx(model=model_path)
File "/home/qqp/miniconda3/envs/toolkit2/lib/python3.8/site-packages/rknn/api/rknn.py", line 163, in load_onnx
return self.rknn_base.load_onnx(model, inputs, input_size_list, input_initial_val, outputs)
File "rknn/api/rknn_log.py", line 349, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper
File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e
ValueError: Traceback (most recent call last):
File "rknn/api/rknn_log.py", line 344, in rknn.api.rknn_log.error_catch_decorator.error_catch_wrapper
File "rknn/api/rknn_base.py", line 1534, in rknn.api.rknn_base.RKNNBase.load_onnx
File "rknn/api/rknn_base.py", line 702, in rknn.api.rknn_base.RKNNBase._create_ir_and_inputs_meta
File "rknn/api/rknn_log.py", line 95, in rknn.api.rknn_log.RKNNLog.e
ValueError: The input shape ['N', 'T', 80] of 'x' is not support!
Please set the 'inputs' / 'input_size_list' parameters of 'rknn.load_onnx', or set the 'dyanmic_input' parameter of 'rknn.config' to fix the input shape!

[csukuangfj]

用sample里提供中英文zipformer模型

这个是 icefall 里面的 pruned_transducer_stateless7_streaming. 目前应该只支持这一个文件夹

任何来自其他文件夹的模型，都是不支持的。比如，你用的 日语 zipformer, 就不是这个文件夹，所以失败了。

[autumnqin]

用sample里提供中英文zipformer模型

这个是 icefall 里面的 pruned_transducer_stateless7_streaming. 目前应该只支持这一个文件夹

任何来自其他文件夹的模型，都是不支持的。比如，你用的 日语 zipformer, 就不是这个文件夹，所以失败了。

有计划支持日语吗？ 或者有教程指导怎么修改一下支持不在这个文件夹的模型吗？

[Davidqian123]

同问，想问一下如何修改可以支持日语zipformer模型的转换