microsoft-cognitive

How to run Microsoft.CognitiveServices.Speech on Windows Server 2012 R2

青春壹個敷衍的年華 提交于 2019-12-06 12:54:15
问题 I need to convert speech from a wav file into text. So I downloaded the sample C# code project from the Quickstart: Recognize speech using Speech service C# SDK page, and followed the instructions on the page. It works in Windows 10, but I need the project to work on Windows Servers 2012 R2 and it doesn't work on Windows Servers 2012 R2. When I run it on Windows Servers 2012 R2, I press the 3 key for the 3. Speech recognition with file input option. But when it tries to execute the following

Bad Argument, Invalid Subscription Key when trying to add key from Azure

情到浓时终转凉″ 提交于 2019-12-06 12:44:38
I am trying to set up my LUIS app in luis.ai (because it seems like I can't set it up in Azure directly?). Anyway, I have created a Language Understanding Intelligent Service (LUIS) (preview) resource, but when I enter one of the keys from that resource into "My Keys" in luis.ai, I get this error: "Bad Argument, Invalid Subscription Key" Also, I just tried to publish an app with the bootstrap key and got the following errors: { "statusCode": 401, "message": "Access denied due to invalid subscription key. Make sure to provide a valid key for an active subscription." } As provided in comments,

Training QnA Maker with API v4.0

江枫思渺然 提交于 2019-12-06 11:17:40
I used to use the preview version of QnA Maker and with it the v3.0 API had this train endpoint which could be used to reinforce a correct answer: https://westus.dev.cognitive.microsoft.com/docs/services/597029932bcd590e74b648fb/operations/597045078eb8131608e2f7a6 Now I'm migrating to QnA Maker GA and it uses the v4.0 API. I cannot find the train endpoint anywhere in the documentation of the v4.0 APi. Does the train endpoint still exist in the v4.0 API? Official reply has been made on Github issue by Prashant Choudhari from Microsoft: We do not have the train API in V4. We are re-thinking this

Getting Different Results via Bing Speech Recognition API (beta) for Same Audio file(.wav)

走远了吗. 提交于 2019-12-06 10:39:24
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

Emotion API Project Oxford base64 image

旧时模样 提交于 2019-12-06 08:34:38
I am trying to make a call to the Emotion Api via JavaScript with in a PhoneGap app. I encoded the image into base64 and verified that the data can be decoded by one of the online tools. this is the code that i found on the web to use. var apiKey = "e371fd4333ccad2"; //(you can get a free key on site this is modified for here) //apiUrl: The base URL for the API. Find out what this is for other APIs via the API documentation var apiUrl = " https://api.projectoxford.ai/emotion/v1.0/recognize "; "file" is the base64 string. function CallAPI(file, apiUrl, apiKey) { // console.log("file=> " +file);

Posting An Image from Webcam to Azure Face Api

痴心易碎 提交于 2019-12-06 02:35:32
I am trying to upload an image that I get from my webcam to the Microsoft Azure Face Api. I get the image from canvas.toDataUrl(‘image/png’) which contains the Data Uri. I change the Content Type to application/octet-stream and when I attach the Data Uri to the post request, I get a Bad Request (400) Invalid Face Image. If I change the attached data to a Blob, I stop receiving errors however I only get back an empty array instead of a JSON object. I would really appreciate any help for pointing me in the right direction. Thanks! Oh you're in such luck, i've just (successfully!) attempted this

Correct Key for Microsoft Cognitive API

做~自己de王妃 提交于 2019-12-05 18:23:23
I am currently trying to do a News Search on the MS Cognitive Services Bing Search API. I have read many docs, but seem to be stuck. Here is the code I'm using: $url = 'https://bingapis.azure-api.net/api/v5/news/search?q=microsoft&mkt=en-us'; $key = '{MY KEY}'; $request_headers = array(); $request_headers[] = 'Ocp-Apim-Subscription-Key: '. $key; $request_headers[] = 'User-Agent: mozilla'; $ch = curl_init($url); curl_setopt($ch, CURLOPT_TIMEOUT, 5); curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 5); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); curl_setopt($ch, CURLOPT_HTTPHEADER, $request_headers)

Use Azure custom-vision trained model with tensorflow.js

偶尔善良 提交于 2019-12-05 02:41:01
问题 I've trained a model with Azure Custom Vision and downloaded the TensorFlow files for Android (see: https://docs.microsoft.com/en-au/azure/cognitive-services/custom-vision-service/export-your-model). How can I use this with tensorflow.js? I need a model (pb file) and weights (json file). However Azure gives me a .pb and a textfile with tags. From my research I also understand that there are also different pb files, but I can't find which type Azure Custom Vision exports. I found the tfjs

Can we build Skype bots for “Skype for Business”?

爱⌒轻易说出口 提交于 2019-12-04 00:28:47
I've seen examples of bot programming that work with "Skype". Is it possible to develop enterprise bots that run on "Skype for Business" using Microsoft's Bot/Cognitive service tools/framework? Skype for Business is not yet supported by Bot Framework . To find all the messaging channels that are supported visit the Bot Framework's documentation site . The Microsoft Bot Framework now officially supports Skype for Business as a channel: Skype for Business Bot Framework (Preview) (As of writing this its in Preview mode, so things may change in the future. But at least its there.) Skype for

Use Azure custom-vision trained model with tensorflow.js

一个人想着一个人 提交于 2019-12-03 17:07:27
I've trained a model with Azure Custom Vision and downloaded the TensorFlow files for Android (see: https://docs.microsoft.com/en-au/azure/cognitive-services/custom-vision-service/export-your-model ). How can I use this with tensorflow.js ? I need a model (pb file) and weights (json file). However Azure gives me a .pb and a textfile with tags. From my research I also understand that there are also different pb files, but I can't find which type Azure Custom Vision exports. I found the tfjs converter . This is to convert a TensorFlow SavedModel (is the *.pb file from Azure a SavedModel?) or