rtf benchmark

funasr/export/models/modules/multihead_att.py

@@ -75,8 +75,10 @@ def preprocess_for_attn(x, mask, cache, pad_fn):
     return x, cache
 
 
-import torch.fx
-torch.fx.wrap('preprocess_for_attn')
+torch_version = float(".".join(torch.__version__.split(".")[:2]))
+if torch_version >= 1.8:
+    import torch.fx
+    torch.fx.wrap('preprocess_for_attn')
 
 
 class MultiHeadedAttentionSANMDecoder(nn.Module):

funasr/runtime/python/benchmark_libtorch.md

@@ -26,35 +26,17 @@ Aishell1 [test set](https://www.openslr.org/33/) , the total audio duration is 3
 
 ## [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) 
 
-### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz   16core-32processor    with avx512_vnni
-
-[//]: # (| concurrent-tasks | processing time(s) |  RTF   | Speedup Rate |)
-
-[//]: # (|:----------------:|:------------------:|:------:|:------------:|)
-
-[//]: # (|  1 (torch fp32)  |        3522        | 0.0976 |     10.3     |)
-
-[//]: # (|  1 (torch int8)  |        1746        | 0.0484 |     20.7     |)
-
-[//]: # (|  32 (torch fp32)  |        236         | 0.0066 |    152.7     |)
-
-[//]: # (|  32 (torch int8)  |        114         | 0.0032 |    317.4     |)
-
-[//]: # (|  64 (torch fp32)  |        235         | 0.0065 |    153.7     |)
-
-[//]: # (|  64 (torch int8)  |        113         | 0.0031 |    319.2     |)
-
 
 ### Intel(R) Xeon(R) Platinum 8269CY CPU @ 2.50GHz   16core-32processor    with avx512_vnni
 
 | concurrent-tasks | processing time(s) |  RTF   | Speedup Rate |
 |:----------------:|:------------------:|:------:|:------------:|
-|  1 (torch fp32)  |        3522        | 0.0976 |     10.3     |
+| 1 (torch fp32)   |        3522        | 0.0976 |     10.3     |
 |  1 (torch int8)  |        1746        | 0.0484 |     20.7     |
-|  32 (torch fp32)  |        236         | 0.0066 |    152.7     |
-|  32 (torch int8)  |        114         | 0.0032 |    317.4     |
-|  64 (torch fp32)  |        235         | 0.0065 |    153.7     |
-|  64 (torch int8)  |        113         | 0.0031 |    319.2     |
+| 32 (torch fp32)  |        236         | 0.0066 |    152.7     |
+| 32 (torch int8)  |        114         | 0.0032 |    317.4     |
+| 64 (torch fp32)  |        235         | 0.0065 |    153.7     |
+| 64 (torch int8)  |        113         | 0.0031 |    319.2     |
 
 
 [//]: # (### Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz    32core-64processor   without avx512_vnni)

funasr/runtime/python/benchmark_onnx.md

@@ -72,3 +72,20 @@ Aishell1 [test set](https://www.openslr.org/33/) , the total audio duration is 3
 |  96 (onnx int8)  |        108         | 0.0030 |    334.1     |
 
 ## [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary)
+
+ ### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz   16core-32processor    with avx512_vnni
+
+| concurrent-tasks | processing time(s) |  RTF   | Speedup Rate |
+|:----------------:|:------------------:|:------:|:------------:|
+|  16 (onnx fp32)  |         91         | 0.0025 |    395.2     |
+|  16 (onnx int8)  |         78         | 0.0022 |    463.0     |
+|  32 (onnx fp32)  |         60         | 0.0017 |    598.8     |
+|  32 (onnx int8)  |         40         | 0.0011 |    892.9     |
+|  64 (onnx fp32)  |         55         | 0.0015 |    653.6     |
+|  64 (onnx int8)  |         31         | 0.0009 |    1162.8    |
+|  96 (onnx fp32)  |         57         | 0.0016 |    632.9     |
+|  96 (onnx int8)  |         33         | 0.0009 |    1098.9    |
+
+[//]: # (|  1 (onnx fp32)   |        2806        | 0.0777 |     12.9     |)
+
+[//]: # (|  1 (onnx int8)   |        1611        | 0.0446 |     22.4     |)