I have an audio recording file, and I want to extract my custom entities recognise data from the audio file.
I searched and noticed Amazon Comprehend service could help me.
To do this, I have to do the following steps:
- I should submit to server and transcribe the file using AWS Transcribe service - it takes about 15~20 seconds.
- I should get the transcribed text and save it to s3 bucket for the Comprehend Analysis Job, because when we create a job, they ask it as input file.
- I should create an Analysis Job with the input file.
- I should wait till the job is finished - it is very slow (about 2 ~ 7 minutes).
- After the job is finished, the output file is output.tar.gz. They give us compressed file, not plain text.
- I should pull the into the local server and the unzip the file and then get the content.
- I should parse the file content as json data.
It takes about 5~15 minutes to do the whole steps. Especially step 4 takes pretty much times.
I want to optimize it as much as possible.
Can you please help me?
Some questions to answer: