I1023 02:23:35.217113  4724 params.h:114] Reading onnx model 
2023-10-23 02:23:36.156021162 [W:onnxruntime:, session_state.cc:1030 VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-10-23 02:23:36.156074381 [W:onnxruntime:, session_state.cc:1032 VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
2023-10-23 02:23:40.334596254 [W:onnxruntime:, session_state.cc:1030 VerifyEachNodeIsAssignedToAnEp] Some nodes were not assigned to the preferred execution providers which may or may not have an negative impact on performance. e.g. ORT explicitly assigns shape related ops to CPU to improve perf.
2023-10-23 02:23:40.334637713 [W:onnxruntime:, session_state.cc:1032 VerifyEachNodeIsAssignedToAnEp] Rerunning with verbose output on a non-minimal build will show node assignments.
I1023 02:23:40.419196  4724 onnx_asr_model.cc:126] Onnx Model Info:
I1023 02:23:40.419270  4724 onnx_asr_model.cc:127] 	encoder_output_size 512
I1023 02:23:40.419274  4724 onnx_asr_model.cc:128] 	num_blocks 12
I1023 02:23:40.419277  4724 onnx_asr_model.cc:129] 	head 8
I1023 02:23:40.419281  4724 onnx_asr_model.cc:130] 	cnn_module_kernel 15
I1023 02:23:40.419283  4724 onnx_asr_model.cc:131] 	subsampling_rate 4
I1023 02:23:40.419286  4724 onnx_asr_model.cc:132] 	right_context 6
I1023 02:23:40.419289  4724 onnx_asr_model.cc:133] 	sos 5537
I1023 02:23:40.419291  4724 onnx_asr_model.cc:134] 	eos 5537
I1023 02:23:40.419294  4724 onnx_asr_model.cc:135] 	is bidirectional decoder 1
I1023 02:23:40.419306  4724 onnx_asr_model.cc:136] 	chunk_size 16
I1023 02:23:40.419309  4724 onnx_asr_model.cc:137] 	num_left_chunks -1
I1023 02:23:40.419312  4724 onnx_asr_model.cc:140] Onnx Encoder:
I1023 02:23:40.419337  4724 onnx_asr_model.cc:44] 	Input 0 : name=chunk type=1 dims=1 -1 80 
I1023 02:23:40.419354  4724 onnx_asr_model.cc:44] 	Input 1 : name=offset type=7 dims=
I1023 02:23:40.419364  4724 onnx_asr_model.cc:44] 	Input 2 : name=att_cache type=1 dims=12 8 -1 128 
I1023 02:23:40.419373  4724 onnx_asr_model.cc:44] 	Input 3 : name=cnn_cache type=1 dims=12 1 512 14 
I1023 02:23:40.419382  4724 onnx_asr_model.cc:65] 	Output 0 : name=output type=1 dims=-1 -1 512 
I1023 02:23:40.419390  4724 onnx_asr_model.cc:65] 	Output 1 : name=r_att_cache type=1 dims=12 8 -1 128 
I1023 02:23:40.419397  4724 onnx_asr_model.cc:65] 	Output 2 : name=r_cnn_cache type=1 dims=12 1 512 -1 
I1023 02:23:40.419401  4724 onnx_asr_model.cc:142] Onnx CTC:
I1023 02:23:40.419409  4724 onnx_asr_model.cc:146] Onnx Rescore:
I1023 02:23:40.419420  4724 params.h:124] Reading unit table ./Resource/units.txt
I1023 02:23:40.464612  4740 decoder_main.cc:40] num frames 307
I1023 02:23:40.465137  4740 asr_decoder.cc:84] Required 67 get 67
I1023 02:23:40.574081  4740 onnx_asr_model.cc:299] testFunc1004:
I1023 02:23:40.596107  4740 asr_decoder.cc:84] Required 64 get 64
I1023 02:23:40.618441  4740 onnx_asr_model.cc:299] testFunc1004:
I1023 02:23:40.631315  4740 asr_decoder.cc:179] Partial CTC result 脚踝河
I1023 02:23:40.631347  4740 decoder_main.cc:63] Partial result: 脚踝河
I1023 02:23:40.631395  4740 asr_decoder.cc:84] Required 64 get 64
I1023 02:23:40.653893  4740 onnx_asr_model.cc:299] testFunc1004:
I1023 02:23:40.667107  4740 asr_decoder.cc:179] Partial CTC result 脚踝河小腿的
I1023 02:23:40.667135  4740 decoder_main.cc:63] Partial result: 脚踝河小腿的
I1023 02:23:40.667176  4740 asr_decoder.cc:84] Required 64 get 64
I1023 02:23:40.689602  4740 onnx_asr_model.cc:299] testFunc1004:
I1023 02:23:40.703166  4740 asr_decoder.cc:179] Partial CTC result 脚踝河小腿的能力变弱
I1023 02:23:40.703200  4740 decoder_main.cc:63] Partial result: 脚踝河小腿的能力变弱
I1023 02:23:40.703249  4740 asr_decoder.cc:84] Required 64 get 48
I1023 02:23:40.742993  4740 onnx_asr_model.cc:299] testFunc1004:
I1023 02:23:40.753594  4740 asr_decoder.cc:179] Partial CTC result 脚踝河小腿的能力变弱
I1023 02:23:40.754094  4740 asr_decoder.cc:179] Partial CTC result 脚踝河小腿的能力变弱
I1023 02:23:40.792695  4740 asr_decoder.cc:64] Rescoring cost latency: 39ms.
I1023 02:23:40.792733  4740 decoder_main.cc:63] Partial result: 脚踝和小腿的能力变弱
I1023 02:23:40.792738  4740 decoder_main.cc:96] test Final result: 脚踝和小腿的能力变弱
I1023 02:23:40.792752  4740 decoder_main.cc:97] Decoded 3091ms audio taken 325ms.
I1023 02:23:40.792986  4724 decoder_main.cc:172] Total: decoded 3091ms audio taken 325ms.
I1023 02:23:40.793023  4724 decoder_main.cc:174] RTF: 0.1051
HIP Warning: kernel (_ZN11onnxruntime4rocm37_BinaryElementWiseRhsPerChannelBatchNIfffNS0_6OP_SubIfffEELi512ELi2EEEvPKT0_PKT1_NS0_11fast_divmodESA_PT_T2_i) launch (512) threads out of range (256), add __launch_bounds__ to kernel define or use --gpu-max-threads-per-block recompile program !