视频提取音频

pip install ffmpeg moviepy

import moviepy.editor as mp
def extract_audio(videos_file_path):
    my_clip = mp.VideoFileClip(videos_file_path)
    my_clip.audio.write_audiofile(f'{videos_file_path}.mp3')

extract_audio(r"C:\Users\killens\Desktop\mda-kk4pp9ip4uwx0iu2.mp4")

python mqtt部署

安装pip install paho-mqtt

from paho.mqtt import client as mqtt_client

client = mqtt_client.Client('kang_py')
client.connect("121.40.244.52")
client.subscribe("ocr")

定义响应事件函数

void on_message():

...

client.on_message = on_message#绑定响应函数

OCR

首先安装对应的pytorch依赖版本：pip3 install torch torchvision torchaudio

再安装easyocr，这样比较快：pip3 install easyocr

依赖环境：base

文件位置：/mnt/dell/kangbowei/java_API/demo.py

执行方式：python /mnt/dell/kangbowei/java_API/demo.py --name 003.jpg #添加文件名称

文件输入目录：/disk2/deploy/upload/deepLearning/open_ocr/input/

文件输入目录：/disk2/deploy/upload/deepLearning/open_ocr/output/

ocr

import easyocr

reader = easyocr.Reader(['ch_sim','en'])

result = reader.readtext(os.path.join(path,'input',img_name))