We are translating a bunch of audio files (i.e. .wav files), we are getting different results on separate systems. The only difference we are receiving is the number conversion is translated to words, however we only need numbers in translated text.
For ex: we have wave file i.e. A-Hydrocort_50_mg-ml.wav
Transcribed Text on System 1: A hydra court 50 milligrams per milliliter.
Transcribed Text on System 2: A hydra court fifty milligrams per milliliter.
We are using the same API call only these are 2 different machines and API itself gives us different response , the Request is exactly the same (just new GUID is generated for every Request).
Here is the piece of code:
string url = "https://speech.platform.bing.com/recognize";
string requestUri = url.Trim(new char[] { '/', '?' });
/* URI Params. Refer to the README file for more information. */
requestUri += @"?scenarios=smd"; // websearch is the other main option.//ulm//catsearch//websearch
requestUri += @"&appid=D4D52672-91D7-4C74-8AD8-42B1D98141A5"; // You must use this ID.
requestUri += @"&locale=en-US"; // We support several other languages. Refer to README file.
requestUri += @"&device.os=Windows OS";
requestUri += @"&version=3.0";
requestUri += @"&format=json";
requestUri += @"&instanceid=565D69FF-E928-4B7E-87DA-9A750B96D9E3";
requestUri += @"&requestid=" + Guid.NewGuid().ToString();
string host = @"speech.platform.bing.com";
//For wave files
string contentType = @"audio/wav; codec=audio/pcm; samplerate=16000";