diff --git a/demos/asr_deployment/README.md b/demos/asr_deployment/README.md index 24489cbaa..2fba264e6 100644 --- a/demos/asr_deployment/README.md +++ b/demos/asr_deployment/README.md @@ -66,6 +66,7 @@ Please see [here](../../speechx/README.md). > CER compute under aishell-test. > RTF compute with feature and decoder, which is more end to end. +> Machine Intel(R) Xeon(R) Gold 6271C CPU @ 2.60GHz avx512_vnni ### FP32 @@ -76,11 +77,19 @@ English -> 0.00 % N=0 C=0 S=0 D=0 I=0 Other -> 100.00 % N=3 C=0 S=3 D=0 I=0 ``` +``` +RTF is: 0.315337 +``` + ### INT8 ``` -Overall -> 5.87 % N=104765 C=98909 S=5711 D=145 I=289 -Mandarin -> 5.86 % N=104762 C=98909 S=5708 D=145 I=289 +Overall -> 5.83 % N=104765 C=98943 S=5675 D=147 I=286 +Mandarin -> 5.83 % N=104762 C=98943 S=5672 D=147 I=286 English -> 0.00 % N=0 C=0 S=0 D=0 I=0 Other -> 100.00 % N=3 C=0 S=3 D=0 I=0 ``` + +``` +RTF is: 0.269674 +``` \ No newline at end of file diff --git a/demos/asr_deployment/README_cn.md b/demos/asr_deployment/README_cn.md index 78246fe2d..7e7adf1d7 100644 --- a/demos/asr_deployment/README_cn.md +++ b/demos/asr_deployment/README_cn.md @@ -66,6 +66,7 @@ > CER 测试集为 aishell-test > RTF 计算包含提特征和解码 +> 测试机器: Intel(R) Xeon(R) Gold 6271C CPU @ 2.60GHz avx512_vnni ### FP32 @@ -76,6 +77,10 @@ English -> 0.00 % N=0 C=0 S=0 D=0 I=0 Other -> 100.00 % N=3 C=0 S=3 D=0 I=0 ``` +``` +RTF is: 0.315337 +``` + ### INT8 ``` diff --git a/speechx/examples/codelab/u2/utils b/speechx/examples/codelab/u2/utils new file mode 120000 index 000000000..23cef9612 --- /dev/null +++ b/speechx/examples/codelab/u2/utils @@ -0,0 +1 @@ +../../../../utils \ No newline at end of file diff --git a/speechx/examples/u2pp_ol/wenetspeech/RESULTS.md b/speechx/examples/u2pp_ol/wenetspeech/RESULTS.md index 2ad985ccc..1bc5b8e80 100644 --- a/speechx/examples/u2pp_ol/wenetspeech/RESULTS.md +++ b/speechx/examples/u2pp_ol/wenetspeech/RESULTS.md @@ -4,6 +4,8 @@ ## U2++ Attention Rescore +> Intel(R) Xeon(R) Gold 6271C CPU @ 2.60GHz, support `avx512_vnni` +> RTF with feature and decoder which is more end to end. ### FP32 #### CER @@ -17,10 +19,6 @@ Other -> 100.00 % N=3 C=0 S=3 D=0 I=0 #### RTF -> RTF with feature and decoder which is more end to end. - -* Intel(R) Xeon(R) Gold 6271C CPU @ 2.60GHz, support `avx512_vnni` - ``` I1027 10:52:38.662868 51665 u2_recognizer_main.cc:122] total wav duration is: 36108.9 sec I1027 10:52:38.662858 51665 u2_recognizer_main.cc:121] total cost:11169.1 sec @@ -29,11 +27,21 @@ I1027 10:52:38.662876 51665 u2_recognizer_main.cc:123] RTF is: 0.309318 ### INT8 +> RTF relative improve 12.8%, which count feature and decoder time. + #### CER ``` -Overall -> 5.87 % N=104765 C=98909 S=5711 D=145 I=289 -Mandarin -> 5.86 % N=104762 C=98909 S=5708 D=145 I=289 +Overall -> 5.83 % N=104765 C=98943 S=5675 D=147 I=286 +Mandarin -> 5.83 % N=104762 C=98943 S=5672 D=147 I=286 English -> 0.00 % N=0 C=0 S=0 D=0 I=0 Other -> 100.00 % N=3 C=0 S=3 D=0 I=0 ``` + +#### RTF + +``` +I1110 09:59:52.551712 37249 u2_recognizer_main.cc:122] total wav duration is: 36108.9 sec +I1110 09:59:52.551717 37249 u2_recognizer_main.cc:123] total decode cost:9737.63 sec +I1110 09:59:52.551723 37249 u2_recognizer_main.cc:124] RTF is: 0.269674 +``` \ No newline at end of file