I was super excited when learning that Google has finally released its official speech API for developers. I have always been amazed by how great Google's speech recognition works in Android, Chrome, and other products.
I created a Google Cloud account, enabled the speech API, and created a few testing scripts following the Google Speech API documentation. The accuracy is super high, but the speed is insanely slow. An 18-second audio file would take their engine around 16 seconds to transcribe! Microsoft Bing Speech API only needs 3-4 seconds to do it!
Has anyone experienced the same? Or is it a problem of my configurations? Any help is highly appreciated!
Here is the code I used:
BASH:
time curl "https://speech.googleapis.com/v1beta1/speech:syncrecognize?key={MY_API_KEY}" --header "Content-Type: application/json" --data '{"config":{"encoding":"FLAC","sample_rate":16000,"language_code":"en-US"},"audio":{"uri":"gs://accobot-speech/new_record.flac"}}'
To date, the best reference for this issue remains still the reply published in the issue tracker for the Google Platform.
Related
I already finish the chatbot, but I have no idea of how to upload it to my website, please, help :)
I tried to look for some code to send to the IT developers, but cannot find it :( And the IT guys are too busy, so I'ld like to get the answer by myself so I can send it to them if I'm not able to apply it. Thank you. (Btw: I'm not an IT person... :( )
Where to start?
The dialog / conversation part of your Watson Assistant part chatbot is available as a REST API.
There are several deployment options available. For the more popular choices the Assistant tooling provides integrations. So if you want to access your chatbot through slack, or facebook messenger or on a word press site then look at the documentation as to how - https://cloud.ibm.com/docs/services/assistant?topic=assistant-deploy-integration-add
If you are developing your own application or web-page, then your developers will need to design the User Interface and handle the quirks of your dialog. eg. Decide how to display images, options etc., all from the API, which is essentially only message in, response out - https://cloud.ibm.com/apidocs/assistant-v2#send-user-input-to-assistant. There are samples available for them to base from - eg. https://github.com/watson-developer-cloud/assistant-intermediate
If your website is using Wordpress, there is a very easy way to deploy the chatbot to it using a wordpress plug in - https://wordpress.org/plugins/conversation-watson/
I am trying to use the Google Speech API to transcribe audio captured from a semi-embedded device. The device supports python scripts, but does not seem to offer any way to allow imports.
I have managed to get the speech API sample program working on my computer, but since I cannot import the necessary modules, I see myself forced to develop a web application that accepts an audio file and returns the transcript.
I am completely new at web development, and so far I have concluded that I'm going to need to use Google App Engine, but beyond that I'm completely lost.
I have identified the following steps, and if someone could point me in the right direction that would be greatly appreciated:
Allow uploading of a flac file to a certain URL.
Upload the flac file to the google speech API and receive the transcription (I'm fairly certain I could manage this myself).
Return the transcription to the device somehow.
I'm not asking for finished code or anything, but it would be nice if somebody could tell me at the very least if what I want to do is possible with the google app engine, or if I need to look for something else.
What you want to do is absolutely possible with Google App Engine. Take a look at the App Engine Python tutorials to get started with the environment etc., but it sounds like what you want will involve an API that accepts a POST with binary data in the body (the FLAC) and then passes that to the Speech API (try the GRPC samples).
Good luck! :)
Does anyone have a link or can provide the code for a Java Google App Engine project which simply interacts with Google Calendar. Say get an event from your calendar.
The Google Sample calendar-appengine-sample does not compile once checkout out from HG and I have tried searching for tutorials and creating my own with only small bits of luck in places.
I have already set up an API Access project to get the client-secrets.json.
So as much as some think this is a poor question it demonstrates that there is not much out there in terms of help with the combination of Java, App Engine and OAuth. I have an ex Google employee at my company and he did agree that it is not as straightforward as it should be.
Based on the reply to my post on the Google Group I decided to use Python where the OAuth2Decorator makes the task trivial.
This was a very useful tutorial: https://developers.google.com/appengine/articles/python/getting_started_with_tasks_api
If you HAVE to use Java these I apologise for this not really helping you, but if you are willing to give Python a go then I recommend the above link and using PyDev with Eclipse.
I'm trying to build a site that updates users' Google Talk statuses from Google App Engine using the built in XMPP Python API (or a third-party one, if one works better than another). I've been looking around for some examples or docs explaining how I would go about doing this, but nothing I find seems to offer a fully functional solution.
App Engine's XMPP Python developer docs suggest that updating a status can be done through the send_presence() method (see here):
xmpp.send_presence(to_jid, status="My app's status")
But, how would this be authenticated? Wouldn't I have to send the users password with the request? (Ideally, I'd like to do so using OAuth as suggested here.) Am I misunderstanding something?
Please excuse me if I'm missing something obvious, here. I'm pretty new to both Google App Engine and XMPP. Unlike a lot of examples I've found online, I don't want to create a chat "robot"; I merely want to change an existing user's Google Talk status. Thanks in advance for any pointers!
You can't change someone else' status using the XMPP API.
You can use the XMPP API to represent yourself, or your users (see the description of XMPP addresses in the GAE XMPP API docs).
You cannot send messages or update the status of a gmail user.
use case: 5 - 30 users simultaniously on a chat.
is it a good idea / is it possible to code this on google app engine?
Until the Channel API is released, you'll have to use polling to do this. When that API is released, App Engine will be (IMO, caveat that I work on the team) a great tool for this.
Note that with 1.3.6 you can use the Channel API for local development so you can at least get started implementing something, though it won't work in prod.
maybe it's a stupid question, but couldn't the GAE Application forward incoming messages to all known clients when they are posted to the server?
Why would that not work?
Laures