This is more like a personal notes for my reference. If it assists anyone it is a bonus.
Assumed that
Then from the command (long) line using curl
if you are behind a firewall with p_user as the user-id and p_passwd is the password. Then the following should do the job!
Assumed that
- You have created an account on blue-mix
- You have obtained the user-id and password (I will call them your_userid, your_password)
- You have a speech file called speech.wav
- You desire to obtain the transcript in the file transcribed_speech.txt
- You have installed curl on your machine
- You are not behind a proxy.com
Then from the command (long) line using curl
curl -u your_userid:your_password -X POST --header "Content-Type: audio/wav" --header "Transfer-Encoding: chunked" --data-binary @speech.wav https://stream.watsonplatform.net/speech-to-text/api/v1/recognize?continuous=true > transcribed_speech.txt
should create the best according to watson speech to text engine transcription of the audio speech.wav in the file transcribed_speech.txt
if you are behind a firewall with p_user as the user-id and p_passwd is the password. Then the following should do the job!
curl --proxy http://p_user:p_passwd@proxy.com:8080 -u your_userid:your_password -X POST --header "Content-Type: audio/wav" --header "Transfer-Encoding: chunked" --data-binary @speech.wav https://stream.watsonplatform.net/speech-to-text/api/v1/recognize?continuous=true > transcribed_speech.txt
Happy speech to text-ing :-)
Sample very rudimentary perl script
Also: See how to similarly use Google ASR
Sample very rudimentary perl script
Also: See how to similarly use Google ASR
Comments