speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

rtf benchmark

Browse Source
This commit is contained in:
游雁 2023-03-17 19:00:59 +08:00
parent cadcf84ce4
commit ed3de87cd9
2 changed files with 28 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
funasr/runtime/python/benchmark_libtorch.md
View File

@ -22,13 +22,38 @@ nohup bash test_rtf.sh &> log.txt &
## [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
### 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 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 8163 CPU @ 2.50GHz 32core-64processor without avx512_vnni
[//]: # (### Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz 32core-64processor without avx512_vnni)
## [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary)

3
funasr/runtime/python/utils/test_rtf.sh
View File

@ -4,7 +4,6 @@ stage=0
scp="/nfs/haoneng.lhn/funasr_data/aishell-1/data/test/wav.scp"
export_root="/nfs/zhifu.gzf/export"
logs_outputs_dir="/nfs/zhifu.gzf/data_debug/test"
split_scps_tool=split_scp.pl
rtf_tool=test_rtf.py
@ -15,7 +14,7 @@ quantize='True' # 'False'
tag=${model_name}/${backend}_${quantize}
!
logs_outputs_dir=${logs_outputs_dir}/${tag}/split$nj
logs_outputs_dir=${export_root}/logs/${tag}/split$nj
mkdir -p ${logs_outputs_dir}
echo ${logs_outputs_dir}