rtf

游雁

2023-03-14 4bdce2285b42b3ac445a60721b3e7e26f78f4ad3

rtf

 funasr/bin/vad_inference_launch.py

@@ -110,7 +110,8 @@
    if mode == "offline":
        from funasr.bin.vad_inference import inference_modelscope
        return inference_modelscope(**kwargs)
    elif mode == "online":
    # elif mode == "online":
    if "param_dict" in kwargs and kwargs["param_dict"]["online"]:
        from funasr.bin.vad_inference_online import inference_modelscope
        return inference_modelscope(**kwargs)
    else:

 funasr/runtime/python/utils/test_rtf.py

New file
@@ -0,0 +1,47 @@

import time
import sys
import librosa
backend=sys.argv[1]
model_dir=sys.argv[2]
wav_file=sys.argv[3]

from torch_paraformer import Paraformer
if backend == "onnxruntime":
    from rapid_paraformer import Paraformer
	
model = Paraformer(model_dir, batch_size=1, device_id="-1")

wav_file_f = open(wav_file, 'r')
wav_files = wav_file_f.readlines()

# warm-up
total = 0.0
num = 100
wav_path = wav_files[0].split("\t")[1].strip() if "\t" in wav_files[0] else wav_files[0].split(" ")[1].strip()
for i in range(num):
    beg_time = time.time()
    result = model(wav_path)
    end_time = time.time()
    duration = end_time-beg_time
    total += duration
    print(result)
    print("num: {}, time, {}, avg: {}, rtf: {}".format(len(wav_path), duration, total/(i+1), (total/(i+1))/5.53))

# infer time
beg_time = time.time()
for i, wav_path_i in enumerate(wav_files):
    wav_path = wav_path_i.split("\t")[1].strip() if "\t" in wav_path_i else wav_path_i.split(" ")[1].strip()
    result = model(wav_path)
end_time = time.time()
duration = (end_time-beg_time)*1000
print("total_time_comput_ms: {}".format(int(duration)))

duration_time = 0.0
for i, wav_path_i in enumerate(wav_files):
    wav_path = wav_path_i.split("\t")[1].strip() if "\t" in wav_path_i else wav_path_i.split(" ")[1].strip()
    waveform, _ = librosa.load(wav_path, sr=16000)
    duration_time += len(waveform)/16.0
print("total_time_wav_ms: {}".format(int(duration_time)))

print("total_rtf: {:.5}".format(duration/duration_time))

 funasr/runtime/python/utils/test_rtf.sh

New file
@@ -0,0 +1,74 @@

nj=64

#:<<!
backend=libtorch
model_dir="/nfs/zhifu.gzf/export/damo/amp_int8/libtorch"
tag=${backend}_fp32
!

:<<!
backend=libtorch
model_dir="/nfs/zhifu.gzf/export/damo/amp_int8/libtorch_fb20"
tag=${backend}_amp_fb20
!

:<<!
backend=onnxruntime
model_dir="/nfs/zhifu.gzf/export/damo/amp_int8/onnx"
tag=${backend}_fp32
!

:<<!
backend=onnxruntime
model_dir="/nfs/zhifu.gzf/export/damo/amp_int8/onnx_dynamic"
tag=${backend}_fp32
!

scp=/nfs/haoneng.lhn/funasr_data/aishell-1/data/test/wav.scp
scp="/nfs/zhifu.gzf/data_debug/test/wav_1500.scp"
local_scp_dir=/nfs/zhifu.gzf/data_debug/test/${tag}/split$nj

rtf_tool=test_rtf.py

mkdir -p ${local_scp_dir}
echo ${local_scp_dir}

split_scps=""
for JOB in $(seq ${nj}); do
    split_scps="$split_scps $local_scp_dir/wav.$JOB.scp"
done

perl egs/aishell/transformer/utils/split_scp.pl $scp ${split_scps}


for JOB in $(seq ${nj}); do
  {
    core_id=`expr $JOB - 1`
    taskset -c ${core_id} python ${rtf_tool} ${backend} ${model_dir} ${local_scp_dir}/wav.$JOB.scp &> ${local_scp_dir}/log.$JOB.txt
  }&

done
wait


rm -rf ${local_scp_dir}/total_time_comput.txt
rm -rf ${local_scp_dir}/total_time_wav.txt
rm -rf ${local_scp_dir}/total_rtf.txt
for JOB in $(seq ${nj}); do
  {
    cat ${local_scp_dir}/log.$JOB.txt | grep "total_time_comput" | awk -F ' '  '{print $2}' >> ${local_scp_dir}/total_time_comput.txt
    cat ${local_scp_dir}/log.$JOB.txt | grep "total_time_wav" | awk -F ' '  '{print $2}' >> ${local_scp_dir}/total_time_wav.txt
    cat ${local_scp_dir}/log.$JOB.txt | grep "total_rtf" | awk -F ' '  '{print $2}' >> ${local_scp_dir}/total_rtf.txt
  }

done

total_time_comput=`cat ${local_scp_dir}/total_time_comput.txt | awk 'BEGIN {max = 0} {if ($1+0>max+0) max=$1 fi} END {print max}'`
total_time_wav=`cat ${local_scp_dir}/total_time_wav.txt | awk '{sum +=$1};END {print sum}'`
rtf=`awk 'BEGIN{printf "%.5f\n",'$total_time_comput'/'$total_time_wav'}'`
speed=`awk 'BEGIN{printf "%.2f\n",1/'$rtf'}'`

echo "total_time_comput_ms: $total_time_comput"
echo "total_time_wav: $total_time_wav"
echo "total_rtf: $rtf, speech: $speed"