I would like to use Google Cloud Speech for recognizing speech in a specific domain (healthcare). I know it already allows to add additional words to the vocabulary of the recognizer (word hints), but this must be done at each API call. Do you know if it can be done separately, by creating a priori your own custom vocabulary?
Last time I checked, Google Cloud Speech only allows users to specify phrase hints via speechContexts in each API call. Some other ASRs such as Microsoft ASR do allow users to train their own language model.
You can check CustomClass, it may help you. Create your own class and use it whatever you want
Related
I am trying to create a automated chat bot using Zendesk that provides answer's based on our FAQ.
I can give the FAQS on json format using our APIs or if there is anyway that i can store it on zendesk i can do that also
here is my requirements
lets a customer comes on chat we based on his category we need to
provide FAQs based on his category
after the FAQs are sent we ask him another question like if he is satisfied or not
If he is not satisfied he must be connected to real human agent.
can someone help me with this like if i need to write a chat bot using the zendesk api on i need to configure some answer bots or something like that
I am embarking on a POC to replace a Power BI dashboard that can’t do all the visualizations we need with a dash app. One major requirement is to be able to pass multiple filters to the app via url in a manner similar to the Power BI capability.
I have tried to research this and see references to URL callbacks and believe this provides the functionality I will need, but I don’t yet understand dash apps well enough to be sure.
I’m not asking how to, just whether or not it can be done. Thanks!
You can. Use the dcc.Location component (docs), and structure any callbacks that need to listen to the URL to have an Input based on that component. You can even pass multiple things with it, such as "filter_1/3/filter_2/5/filter_3/1" and then .split('/') to break up the string and parse the values.
does anybody know if there is a way how to create a label for a keyword using Google Ads API? It can be done using the web interface and apparently it could be done using the Adwords API, but I can't find a way how to do it using Google Ads API so I don't know if it's a feature which they didn't implement or if I'm blind.
Their documentation says
Labels allow you to categorize your campaigns, ad groups, ads, and keywords, and use those categories to simplify your workflow in a variety of ways.
which would suggest that it CAN be done, however below on the same page it states
You can assign labels to your campaigns, customers, ad groups, criteria, or ads.
No word about keywords. I am working with PHP / Laravel and I am using their official php package for the API communication. The package has classes like CampaignLabelOperation, CustomerLabelOperation, AdGroupLabelOperation, etc. but NO "KeywordLabelOperation".
Anybody have a clue if I just can't find it or whatever I could do? Thanks a lot for any help
Technically speaking, Keywords are Ad Group Criteria. Therefore, you'd need to use the AdGroupCriterionLabelService's MutateAdGroupCriterionLabels to create a keyword label.
I am building a recommendation engine and I want that more dynamic. I wanna use google analytic data along with data I have to give users a good recommendation by capturing user's details automatically. is there any particular method for doing that or to blend both google analytic data and local data to work my recommendation engine more dynamically?
You can collect the search terms in the engine inside your site (if they are defined in the URL, i.e. in querystring, you can specify the parameter and collect them in the dedicated report, otherwise if they are inside the path you can use a filter and extract them).
You can then add them manually or dynamically to your database to offer better search results.
I want to know what API is avaiable to search inside video archive by specifying a text query (like TalkMiner does).
There is no API for search specifically but you can quickly cook an application like Talkminer by joining two components - speech recognition engine and an indexer. For speech recognition you can use any avaialble engine like CMUSphinx, you first transcribe all the audio you need to search in.
For indexing you can use any indexing engine like Apache Solr. Just put the automatic transcriptions into the indexer and provide the query interface.
You can check Koemei (https://koemei.com/). It's a service that you can use to index on demand videos and search inside them for specific moments of interest. Koemei also has search embed code for videos which you can embed on any website. And the service provides API you can use.