microsoft-cognitive

问题 I have implemented a chat on a web page, with the possibility to use Speech to text, using Azure Speech API. It works fine but I don't understand where I can set the language understood by the API. I want it to understand french, but when I talk in french, it transcripts in english words with familiar sound. How / Where I can I set the language ? I precise that I'm not the one who set up the service on Azure dashboard. 回答1: There is a locale parameter that you can use optionally like the

问题 I'm using custom Vision ( https://www.customvision.ai ) to train a model for object recognition. After 10 Iterations of training it suddenly stopped loading. I always export it as onnx and load it on the HoloLens (with this tutorial: https://mtaulty.com/2018/03/29/third-experiment-with-image-classification-on-windows-ml-from-uwp-on-hololens-in-unity/ ). And it worked for quite some time (though the results weren't perfect), but after I continued to train the model to find the things better it

问题 I have built an Azure Custom Vision model using ~ 5000 of my own domain-specific images and a set of ~ 30 hierarchical and non-hierarchical labels. I am not sure how best to organize my label zoo in this particular multi-label classification problem. The best approach (see e.g. https://www.researchgate.net/publication/225379571_A_Tutorial_on_Multi-label_Classification_Techniques and https://towardsdatascience.com/journey-to-the-center-of-multi-label-classification-384c40229bff) must depend on

问题 Here is what I've been trying: subscription_key = "***" assert subscription_key face_api_url = 'https://southeastasia.api.cognitive.microsoft.com/face/v1.0/verify' headers = {'Ocp-Apim-Subscription-Key': subscription_key,'Content-Type':'application/json'} params = { "faceId1": "a1cadf80-d780-4b6a-8cef-717548a07e51", "faceId2": "05113848-2c22-4116-8a30-5cde938eec61" } import requests from pprint import pprint response = requests.post(face_api_url, headers=headers, params=params) faces =

问题 I'm trying to use the Academic Knowledge Graph / APIs, but haven't found a way to get an API key for it. Initially, I thought the subscription key was one of two "keys" I was given at a certain point, but they didn't work. I'm having trouble finding where those keys are exactly now. However, I did find a link to the docs: https://dev.labs.cognitive.microsoft.com/docs/services/56332331778daf02acc0a50b/operations/565d9001ca73072048922d97. Here it shows a URL to get a key: That URL is: https:/

问题 The Bing spell check API has a 10,000 char limit for the chunk of text that the request would like to do a spell check [mode=spell] or proof read [mode=proof(default)]. However I am running into an issue where a chunk of misspelt text clearly under the limit of 10k, does not return back with flagged tokens in a spell check request, but does return back in the proof read request. What gives? Is there a lower limit for Spell check? Output for both requests below. I am using POST in both cases

问题 I want to use the new MS Speech Translation API, but I am working with Go so there is no SDK. I have a WebSockets implementation for the previous Translator Speech API, so raw WebSocket are no issue. The documentation states that it is using WebSockets, but I was unable to find the endpoints in the documentation. Does anyone know what are the WS endpoints and their path/header parameters? EDIT: The documentation also says: "If you already have code that uses Bing Speech or Translator Speech

问题 From the documentation here: https://msdn.microsoft.com/en-us/library/dn760793.aspx It says: totalEstimatedMatches: The estimated number of news articles that are relevant to the query. Use this number along with the count and offset query parameters to page the results. However, there are some serious issues. 1.The returned number of results is ALWAYS less than the requested number in the "count" variable. For example, setting a count=100 results in only 75 results. 2.What's more, even

问题 I am trying to upload an image to the Microsoft Computer Vision API from a mobile device, but I am constantly receiving a 400 Bad Request for Invalid File Format "Input data is not a valid image". The documentation states that I can send the data as application/octet-stream in the following form: [Binary image data] I have the data of the image in terms of base64 encoding ("/9j/4AAQSkZJ.........."), and I also have the image as a FILE_URI, but I can't seem to figure out the format in which to

问题 I'd like to test Microsoft Project Oxford Speech recognition API, but I don't know where or how to get the client_id. I'm trying to test Search API. First, I'm trying to get a token to use the service: curl -d -i "https://oxford-speech.cloudapp.net/token/issueToken?grant_type=client_credentials&client_id=123&client_secret=456scope=https%3A%2F%2Fspeech.platform.bing.com" { "statusCode": 401, "message": "Access denied due to invalid subscription key. Make sure you are subscribed to an API you